INDEX

Explanations

phrases related to tagging or labeling

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "tag."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ITNESS

-0.77

theless

-0.75

undai

-0.70

 Seym

-0.70

isky

-0.68

icago

-0.67

 sclerosis

-0.67

 Monetary

-0.63

 Reverend

-0.63

 conflic

-0.62

POSITIVE LOGITS

ged

1.13

gers

1.13

tags

1.04

alog

1.03

gery

1.02

tag

1.02

ging

0.88

ger

0.87

strip

0.87

liam

0.87

Activations Density 0.019%

phrases related to tagging or labeling

occurrences of the word "tag."

No Comments

No Known Activations