INDEX

Explanations

words related to modifications or alterations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'k' in the text

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

 mosqu

-0.83

 behavi

-0.71

 emergencies

-0.68

 Harm

-0.65

 Palestin

-0.65

 decay

-0.64

 contraceptives

-0.63

ãĥ¯

-0.63

 CLSID

-0.62

 recreate

-0.62

POSITIVE LOGITS

ansas

1.18

rieg

1.16

idding

1.04

won

1.00

irk

0.96

oe

0.96

anski

0.95

0.94

orea

0.94

ulk

0.93

Activations Density 0.025%

words related to modifications or alterations

occurrences of the letter 'k' in the text

No Comments

No Known Activations