INDEX

Explanations

mentions of places or proper nouns beginning with "Cap"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Cap" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

hower

-0.97

ĪĴ

-0.87

 silence

-0.81

¿½

-0.75

perse

-0.71

theless

-0.71

td

-0.71

cause

-0.70

selves

-0.70

UGE

-0.67

POSITIVE LOGITS

itol

1.38

itals

1.20

illary

1.18

acity

1.13

rices

1.08

rice

1.08

uchin

1.05

aic

1.03

abilities

1.01

itan

1.00

Activations Density 0.017%

mentions of places or proper nouns beginning with "Cap"

occurrences of the word "Cap" in various contexts

No Comments

No Known Activations