INDEX

Explanations

references to specific numbers and statistical information

oai_token-act-pair · gpt-3.5-turbo

mentions of individuals, organizations, or specific entities involved in issues or events

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

addon

-0.61

venge

-0.57

ãĥĺãĥ©

-0.55

frac

-0.54

0000000000000000

-0.53

PHOTOS

-0.53

Dialogue

-0.53

metadata

-0.50

icon

-0.50

Status

-0.50

POSITIVE LOGITS

 anecd

0.76

 recommends

0.74

 researchers

0.70

 theor

0.69

 study

0.69

TED

0.68

 diagrams

0.65

 researcher

0.65

 recently

0.65

 coined

0.64

Activations Density 1.596%

references to specific numbers and statistical information

mentions of individuals, organizations, or specific entities involved in issues or events

No Comments

No Known Activations