INDEX

Explanations

prefixes followed by a hyphen and a word, potentially related to negative or problematic situations

oai_token-act-pair · gpt-3.5-turbo

negative connotations or outcomes associated with actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Burr

-0.79

 Confederation

-0.79

 Norris

-0.66

 revised

-0.64

 clenched

-0.64

 Chambers

-0.63

cir

-0.63

 Harrington

-0.63

 Debor

-0.62

 Nicarag

-0.62

POSITIVE LOGITS

based

1.29

advertising

1.16

to

1.15

level

1.12

through

1.11

sized

1.11

related

1.10

style

1.06

type

1.05

tun

1.04

Activations Density 0.181%

prefixes followed by a hyphen and a word, potentially related to negative or problematic situations

negative connotations or outcomes associated with actions

No Comments

No Known Activations