INDEX

Explanations

phrases describing actions or states of an individual

oai_token-act-pair · gpt-3.5-turbo

information about a person's early life and personal history

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

emale

-0.75

 Composite

-0.65

selves

-0.65

ogether

-0.65

 discrep

-0.63

anwhile

-0.58

nesday

-0.58

[*

-0.56

 respectively

-0.56

aminer

-0.54

POSITIVE LOGITS

 himself

0.61

Minecraft

0.55

cffffcc

0.54

 apolog

0.53

 solo

0.51

 Nasa

0.51

 Annotations

0.49

CVE

0.49

zbollah

0.49

ihad

0.48

Activations Density 0.575%

phrases describing actions or states of an individual

information about a person's early life and personal history

No Comments

No Known Activations