INDEX

Explanations

proper nouns, especially related to specific individuals

oai_token-act-pair · gpt-3.5-turbo

names of individuals and companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ocker

-0.75

ative

-0.69

ohyd

-0.69

 Kimmel

-0.67

MLG

-0.65

 Kamp

-0.64

 Cambodia

-0.63

 Barkley

-0.63

 Donkey

-0.63

[+

-0.62

POSITIVE LOGITS

inarily

0.92

scl

0.83

bent

0.81

 lapt

0.81

gaard

0.78

sites

0.77

rez

0.75

oir

0.74

need

0.74

 Coul

0.74

Activations Density 0.069%

proper nouns, especially related to specific individuals

names of individuals and companies

No Comments

No Known Activations