INDEX

Explanations

mentions of tags

oai_token-act-pair · gpt-3.5-turbo

instances of the word "tag" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

isky

-0.78

 Seym

-0.72

¬¼

-0.70

theless

-0.70

undai

-0.70

 perspect

-0.64

orld

-0.64

Rae

-0.62

icago

-0.62

gow

-0.62

POSITIVE LOGITS

gers

1.23

ged

1.23

gery

1.11

alog

1.05

ger

1.03

ging

1.02

tag

1.00

tags

0.96

strip

0.92

liam

0.90

Activations Density 0.028%

mentions of tags

instances of the word "tag" and its variations

No Comments

No Known Activations