INDEX

Explanations

keywords related to the dissemination or spreading of information

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "word" and its variations in context

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

urdue

-0.85

ause

-0.79

uits

-0.77

hematic

-0.76

ogie

-0.72

oos

-0.72

amiya

-0.71

assi

-0.70

ulpt

-0.68

uming

-0.68

POSITIVE LOGITS

NEWS

0.86

 reports

0.85

 regarding

0.80

 rumours

0.79

tale

0.79

ariat

0.76

 concerning

0.75

tid

0.75

 rumors

0.75

confirmed

0.73

Activations Density 0.150%

keywords related to the dissemination or spreading of information

occurrences of the word "word" and its variations in context

No Comments

No Known Activations