INDEX

Explanations

mentions of the word "pumpkin."

oai_token-act-pair · gpt-3.5-turbo

variations and mentions of pumpkins

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

lasses

-0.81

gencies

-0.78

enance

-0.77

ying

-0.76

ysis

-0.72

ugu

-0.72

culosis

-0.71

 Bulg

-0.69

rets

-0.69

ges

-0.66

POSITIVE LOGITS

 spice

1.05

fruit

0.86

 Spice

0.85

apolis

0.83

TERN

0.79

burg

0.76

 Pumpkin

0.75

cone

0.75

asant

0.75

 pard

0.75

Activations Density 0.037%

mentions of the word "pumpkin."

variations and mentions of pumpkins

No Comments

No Known Activations