INDEX

Explanations

keywords related to decision-making or consideration

oai_token-act-pair · gpt-3.5-turbo

instances of the word "considering."

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

ijk

-0.73

Buzz

-0.67

lua

-0.65

dx

-0.63

blogspot

-0.62

baugh

-0.60

oooo

-0.60

soever

-0.60

\-

-0.59

bell

-0.58

POSITIVE LOGITS

ļéĨĴ

1.01

 reconsider

0.89

 feasibility

0.89

soDeliveryDate

0.86

ndum

0.84

 whether

0.82

merce

0.79

ricular

0.77

 aloud

0.74

 deliber

0.73

Activations Density 0.067%

keywords related to decision-making or consideration

instances of the word "considering."

No Comments

No Known Activations