INDEX

Explanations

mentions of the word "shack."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "shack" and related terms

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

ppo

-0.74

osate

-0.72

assic

-0.71

cker

-0.69

endars

-0.66

ague

-0.66

ppa

-0.65

icter

-0.65

teness

-0.64

ocious

-0.63

POSITIVE LOGITS

eering

1.03

lain

0.94

yrinth

0.93

nai

0.92

eers

0.91

nesses

0.88

mone

0.87

intosh

0.85

ledge

0.84

neys

0.84

Activations Density 0.042%

mentions of the word "shack."

occurrences of the word "shack" and related terms

No Comments

No Known Activations