INDEX

Explanations

city or university names

oai_token-act-pair · gpt-3.5-turbo

mentions of specific geographic locations, particularly cities and states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

crow

-0.74

epad

-0.71

club

-0.69

agers

-0.68

cream

-0.68

lasses

-0.67

lain

-0.66

ror

-0.66

thood

-0.66

croft

-0.66

POSITIVE LOGITS

 Falls

1.34

anooga

0.90

 Niagara

0.89

 Montana

0.84

 Idaho

0.80

 Superior

0.77

shire

0.77

 Mills

0.77

sylvania

0.73

atoon

0.73

Activations Density 0.065%

city or university names

mentions of specific geographic locations, particularly cities and states

No Comments

No Known Activations