INDEX

Explanations

phrases indicating repeated events or actions

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate repetition or frequency of occurrence

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

XT

-0.85

Reviewer

-0.83

agra

-0.77

Marginal

-0.71

aceous

-0.69

ourt

-0.69

 heirs

-0.68

ITAL

-0.67

andr

-0.65

ains

-0.65

POSITIVE LOGITS

 consecut

1.02

points

0.87

 throughout

0.80

cale

0.80

coded

0.78

 apiece

0.74

orial

0.71

 before

0.69

pan

0.69

manship

0.68

Activations Density 0.045%

phrases indicating repeated events or actions

phrases that indicate repetition or frequency of occurrence

No Comments

No Known Activations