INDEX

Explanations

references to specific geographic locations, particularly Staten Island

oai_token-act-pair · gpt-3.5-turbo

references to Staten Island and its associated context

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

ioned

-0.84

hered

-0.79

kered

-0.79

cius

-0.79

riott

-0.77

ivia

-0.76

Leod

-0.74

wagen

-0.72

eners

-0.72

vP

-0.72

POSITIVE LOGITS

 borough

1.13

 Borough

1.10

 subway

0.82

 Islanders

0.81

 Armory

0.77

 Staten

0.76

 skyline

0.74

 Island

0.73

 Citiz

0.73

 sidewalk

0.73

Activations Density 0.021%

references to specific geographic locations, particularly Staten Island

references to Staten Island and its associated context

No Comments

No Known Activations