INDEX

Explanations

apologies or expressions of regret

oai_token-act-pair · gpt-3.5-turbo

expressions of apology and regret

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

lite

-0.89

fman

-0.84

eele

-0.78

irtual

-0.77

ngth

-0.77

kefeller

-0.76

hill

-0.74

itect

-0.73

rients

-0.73

Goal

-0.73

POSITIVE LOGITS

 sorry

0.87

 missed

0.83

 unres

0.82

sorry

0.80

 inconven

0.78

 omission

0.77

 miscar

0.76

Chr

0.72

 Sorry

0.72

 Crimes

0.72

Activations Density 0.127%

apologies or expressions of regret

expressions of apology and regret

No Comments

No Known Activations