INDEX

Explanations

phrases or words related to tags

oai_token-act-pair · gpt-3.5-turbo

the word "tag" and its variations, indicating focus on tagging or labels

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

theless

-0.77

undai

-0.72

icago

-0.72

 Seym

-0.72

ITNESS

-0.71

 Reverend

-0.66

isky

-0.65

¬¼

-0.63

gow

-0.62

 Lumpur

-0.62

POSITIVE LOGITS

ged

1.17

gers

1.12

alog

1.06

tag

1.03

gery

1.02

tags

1.00

ging

0.90

ger

0.88

strip

0.88

TAG

0.87

Activations Density 0.018%

phrases or words related to tags

the word "tag" and its variations, indicating focus on tagging or labels

No Comments

No Known Activations