INDEX

Explanations

words related to comparison or proportion

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "relative" and phrases related to comparative relationships or measures

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

spr

-0.99

ERG

-0.89

storm

-0.87

eret

-0.82

enegger

-0.82

iere

-0.81

inis

-0.80

Ì¶

-0.79

vous

-0.77

Ö¼

-0.76

POSITIVE LOGITS

 humidity

1.09

 pronoun

0.87

 ease

0.85

 newcomer

0.85

 pronouns

0.84

 importance

0.83

 autonomy

0.82

 pressures

0.81

 anonymity

0.80

 newcom

0.80

Activations Density 0.012%

words related to comparison or proportion

occurrences of the word "relative" and phrases related to comparative relationships or measures

No Comments

No Known Activations