INDEX

Explanations

words related to communication, such as speakers, listeners, reports, and feedback

oai_token-act-pair · gpt-3.5-turbo

repeated punctuation marks, particularly commas, indicating a pattern or emphasis in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

units

-0.65

ļéĨĴ

-0.64

Goal

-0.59

interstitial

-0.59

aha

-0.59

Override

-0.59

Reward

-0.59

Reply

-0.57

account

-0.57

Engineers

-0.55

POSITIVE LOGITS

huh

1.06

 however

1.03

sir

0.87

 albeit

0.86

 please

0.82

 though

0.81

eh

0.80

 meanwhile

0.80

yes

0.73

 yeah

0.70

Activations Density 0.463%

words related to communication, such as speakers, listeners, reports, and feedback

repeated punctuation marks, particularly commas, indicating a pattern or emphasis in the text

No Comments

No Known Activations