INDEX

Explanations

phrases indicating a sense of belonging or compatibility

oai_token-act-pair · gpt-3.5-turbo

phrases indicating fitting or belonging within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

pora

-0.67

iger

-0.66

oa

-0.65

gov

-0.63

xiety

-0.62

uj

-0.62

anta

-0.61

bach

-0.61

ãĥį

-0.61

ipal

-0.59

POSITIVE LOGITS

 bounds

0.88

 precon

0.84

 snug

0.81

 criteria

0.75

 curve

0.75

 stereotype

0.73

 criterion

0.72

Square

0.72

 confines

0.71

Interstitial

0.71

Activations Density 0.196%

phrases indicating a sense of belonging or compatibility

phrases indicating fitting or belonging within a context

No Comments

No Known Activations