INDEX

Explanations

individual words or short phrases related to administrative or procedural terms

oai_token-act-pair · gpt-3.5-turbo

references to specific sections or parts of a content piece

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

berus

-0.69

apons

-0.67

 groom

-0.63

 elbows

-0.63

 Commissioners

-0.60

ãĤī

-0.60

ministic

-0.59

ITH

-0.59

 minded

-0.59

 sugg

-0.56

POSITIVE LOGITS

icularly

1.16

ially

1.15

ners

1.13

icipated

1.00

nered

1.00

icular

0.97

ner

0.96

ials

0.93

ridge

0.90

isans

0.88

Activations Density 0.039%

individual words or short phrases related to administrative or procedural terms

references to specific sections or parts of a content piece

No Comments

No Known Activations