INDEX

Explanations

words related to legislative action or legal processes

oai_token-act-pair · gpt-3.5-turbo

words related to disabilities and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

orgetown

-0.79

stadt

-0.74

itia

-0.74

etts

-0.72

etsk

-0.71

edia

-0.70

 Niet

-0.69

apo

-0.68

shop

-0.68

thora

-0.67

POSITIVE LOGITS

perse

0.71

abled

0.70

ead

0.68

ĸļ

0.68

________________________

0.64

xual

0.61

abouts

0.61

 morp

0.60

 Creatures

0.60

 Seah

0.59

Activations Density 0.091%

words related to legislative action or legal processes

words related to disabilities and their implications

No Comments

No Known Activations