INDEX

Explanations

expressions related to emotional responses or opinions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "sentiment" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ARDS

-0.82

DERR

-0.74

ARD

-0.74

ummies

-0.72

drivers

-0.65

 Mamm

-0.65

ctic

-0.64

 navig

-0.63

verning

-0.62

 Appendix

-0.60

POSITIVE LOGITS

ality

1.25

 sentiments

1.02

 sentiment

0.90

ally

0.88

uated

0.88

 expressed

0.84

igue

0.79

uation

0.78

uality

0.77

ual

0.76

Activations Density 0.031%

expressions related to emotional responses or opinions

instances of the word "sentiment" and its variations

No Comments

No Known Activations