INDEX

Explanations

references to news reporting or journalistic content

oai_token-act-pair · gpt-3.5-turbo

occurrences of the token "0" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bould

-0.63

 hereafter

-0.59

iod

-0.58

milo

-0.58

forth

-0.58

bly

-0.57

 diction

-0.55

iod

-0.54

orically

-0.54

 plaster

-0.54

POSITIVE LOGITS

 SHARES

1.11

 Expand

0.83

 Shares

0.80

 Comments

0.66

 Explicit

0.64

xff

0.63

\\\\\\\\

0.62

Password

0.62

ãĥĥ

0.61

Activations Density 0.034%

references to news reporting or journalistic content

occurrences of the token "0" in various contexts

No Comments

No Known Activations