INDEX

Explanations

verbs related to glorification or approval

oai_token-act-pair · gpt-3.5-turbo

variations of the root word "glorify" and its related forms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ranging

-0.81

olit

-0.75

enegger

-0.72

utterstock

-0.69

apter

-0.66

izoph

-0.65

 trave

-0.65

dimension

-0.65

itta

-0.65

inson

-0.64

POSITIVE LOGITS

rices

0.75

 ceremonies

0.70

AFTA

0.70

SHIP

0.68

eous

0.64

rics

0.64

 perjury

0.63

 Ones

0.62

ifiers

0.61

 acceptance

0.61

Activations Density 0.179%

verbs related to glorification or approval

variations of the root word "glorify" and its related forms

No Comments

No Known Activations