INDEX

Explanations

phrases related to contrasts or comparisons

oai_token-act-pair · gpt-3.5-turbo

contrasts and comparisons within narratives or statements

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

 supers

-0.58

 rush

-0.58

ction

-0.55

orth

-0.53

utions

-0.52

 Probe

-0.51

 assembled

-0.51

 phased

-0.50

rave

-0.49

 fetch

-0.49

POSITIVE LOGITS

etc

1.14

etc

1.10

 Lastly

0.84

ĪĴ

0.79

SPONSORED

0.78

edIn

0.77

 Finally

0.75

 ..............

0.72

Â¯Â¯Â¯Â¯

0.71

whatever

0.70

Activations Density 0.478%

phrases related to contrasts or comparisons

contrasts and comparisons within narratives or statements

No Comments

No Known Activations