INDEX

Explanations

verbs or phrases indicating observation or perception

oai_token-act-pair · gpt-3.5-turbo

verbs indicating presence or appearance

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

shaw

-0.83

EStreamFrame

-0.77

ricular

-0.73

ests

-0.73

Ã§a

-0.71

dp

-0.70

rament

-0.69

akable

-0.65

aign

-0.64

pping

-0.64

POSITIVE LOGITS

Pause

0.80

ãĤ¤ãĥĪ

0.73

 poised

0.71

ively

0.68

 contradictions

0.68

iary

0.67

Crash

0.66

Magikarp

0.64

ibility

0.64

 destined

0.61

Activations Density 0.042%

verbs or phrases indicating observation or perception

verbs indicating presence or appearance

No Comments

No Known Activations