INDEX

Explanations

the word "arguably."

oai_token-act-pair · gpt-3.5-turbo

the word "arguably" and its variations, which indicate subjective assessments or opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ters

-0.73

nen

-0.69

ysis

-0.69

iths

-0.66

raged

-0.66

aeus

-0.65

iak

-0.65

iry

-0.65

spr

-0.65

letter

-0.65

POSITIVE LOGITS

 underrated

0.78

 unemploy

0.78

 deserved

0.76

 metic

0.74

Effective

0.70

©¶æ¥µ

0.70

 underestimated

0.69

 minded

0.69

interstitial

0.69

 overlooked

0.68

Activations Density 0.018%

the word "arguably."

the word "arguably" and its variations, which indicate subjective assessments or opinions

No Comments

No Known Activations