INDEX

Explanations

words related to violent actions or tools

oai_token-act-pair · gpt-3.5-turbo

gerunds or verbs presented in a 'ed' form

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 modification

-0.80

oller

-0.72

 escalation

-0.72

 blaze

-0.70

 Schumer

-0.69

 Daniels

-0.66

 Dickinson

-0.66

 Scotia

-0.66

 flick

-0.66

Wiz

-0.66

POSITIVE LOGITS

paren

1.17

earth

1.04

bodied

1.03

by

1.03

upon

1.01

enough

1.00

looking

1.00

fee

0.99

dead

0.98

through

0.96

Activations Density 0.043%

words related to violent actions or tools

gerunds or verbs presented in a 'ed' form

No Comments

No Known Activations