INDEX

Explanations

punctuation marks and negative sentiment in the text

oai_token-act-pair · gpt-3.5-turbo

empty or placeholder content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 manif

-0.66

 shove

-0.65

 standing

-0.65

 decon

-0.61

 scissors

-0.61

 compar

-0.60

 prest

-0.60

 clen

-0.59

amorph

-0.57

 goodness

-0.57

POSITIVE LOGITS

=-=-=-=-=-=-=-=-

0.93

webkit

0.91

=-=-=-=-

0.91

 Advertisement

0.89

CLUS

0.72

 Updated

0.71

HOU

0.69

immune

0.69

Updated

0.69

COL

0.69

Activations Density 0.018%

punctuation marks and negative sentiment in the text

empty or placeholder content

No Comments

No Known Activations