INDEX

Explanations

words that appear to be names of people or characters

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and initials

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

ModLoader

-0.84

rency

-0.76

enegger

-0.74

pection

-0.74

theless

-0.73

externalActionCode

-0.70

heit

-0.70

ornia

-0.70

netflix

-0.68

kefeller

-0.68

POSITIVE LOGITS

henko

0.82

opoulos

0.77

ovsky

0.77

akis

0.77

jad

0.77

Ö¼

0.77

emort

0.76

kov

0.74

uly

0.66

 Kear

0.66

Activations Density 0.282%

words that appear to be names of people or characters

proper nouns, particularly names and initials

No Comments

No Known Activations