INDEX

Explanations

words related to suffocation and related medical conditions

oai_token-act-pair · gpt-3.5-turbo

words related to suffering

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

REDACTED

-0.75

Ô

-0.73

 McMaster

-0.67

FIX

-0.66

displayText

-0.66

 Bard

-0.65

 Dragonbound

-0.65

videos

-0.65

TAG

-0.64

 Ally

-0.64

POSITIVE LOGITS

erers

1.19

ocating

0.96

erer

0.95

 suff

0.91

iments

0.91

ishers

0.91

ishes

0.81

ishing

0.80

ignt

0.80

inger

0.79

Activations Density 0.005%

words related to suffocation and related medical conditions

words related to suffering

No Comments

No Known Activations