INDEX

Explanations

mentions of the word "shots."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "shots."

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

rador

-0.85

gres

-0.78

Myth

-0.71

ŃĶ

-0.70

ricular

-0.65

ding

-0.65

adian

-0.64

 feasibility

-0.63

yrinth

-0.63

ply

-0.62

POSITIVE LOGITS

guns

0.97

gun

0.97

 shots

0.97

hell

0.91

shot

0.90

 shot

0.88

creen

0.87

 Shots

0.86

 fired

0.86

shots

0.85

Activations Density 0.014%

mentions of the word "shots."

occurrences of the word "shots."

No Comments

No Known Activations