INDEX

Explanations

mentions of people or entities being part of a group or category

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a group or collective inclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 anytime

-0.73

ption

-0.61

 translates

-0.61

rimp

-0.60

bs

-0.58

hs

-0.58

ario

-0.57

 noses

-0.57

ober

-0.56

bsite

-0.56

POSITIVE LOGITS

 those

0.93

those

0.78

Ĥ¬

0.77

 dozens

0.76

Ĳ

0.76

 hundreds

0.74

 thousands

0.72

st

0.69

 billions

0.68

 several

0.68

Activations Density 0.033%

mentions of people or entities being part of a group or category

phrases that indicate a group or collective inclusion

No Comments

No Known Activations