INDEX

Explanations

mentions of specific names or titles

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific repeated character or pattern

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 succeeding

-0.76

 unpre

-0.73

 revived

-0.71

EStream

-0.70

arial

-0.68

 administering

-0.65

 bolst

-0.65

ioch

-0.64

 tion

-0.64

displayText

-0.64

POSITIVE LOGITS

atts

1.17

restling

1.08

ashington

1.08

itness

1.07

atson

1.06

reck

1.03

OW

1.02

ITH

1.02

edge

1.01

avy

1.00

Activations Density 0.022%

mentions of specific names or titles

occurrences of a specific repeated character or pattern

No Comments

No Known Activations