INDEX

Explanations

phrases related to people and places, especially names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names associated with specific individuals or locations

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

 hardened

-0.70

 psychic

-0.69

 Gemini

-0.66

 separation

-0.65

ACTED

-0.65

Chr

-0.64

 mort

-0.62

 respectful

-0.62

psy

-0.58

 fateful

-0.58

POSITIVE LOGITS

aii

1.40

haw

1.40

keye

1.08

inson

1.04

intosh

0.98

daq

0.97

vine

0.96

awks

0.95

kins

0.93

igans

0.91

Activations Density 0.006%

phrases related to people and places, especially names

proper nouns, particularly names associated with specific individuals or locations

No Comments

No Known Activations