INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

instances of the acronym "BO"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

mary

-0.83

gew

-0.81

ional

-0.78

imental

-0.75

geist

-0.72

uality

-0.72

orial

-0.72

iment

-0.71

ivities

-0.71

enced

-0.71

POSITIVE LOGITS

BO

1.17

ARD

0.99

OTH

0.97

OTS

0.97

OSE

0.93

bably

0.92

OM

0.89

OT

0.89

ARDS

0.89

INC

0.89

Activations Density 0.005%

proper nouns

instances of the acronym "BO"

No Comments

No Known Activations