INDEX

Explanations

technical terms related to science or medicine

oai_token-act-pair · gpt-3.5-turbo

names of specific places and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 busted

-0.76

AUD

-0.75

 Sabha

-0.71

Obj

-0.70

udeau

-0.68

STD

-0.66

ICLE

-0.65

lishes

-0.64

PsyNetMessage

-0.64

ACTED

-0.62

POSITIVE LOGITS

pa

0.68

aukee

0.66

 Palace

0.64

ople

0.63

 Penguins

0.63

stown

0.63

nes

0.62

hire

0.62

 Gardens

0.60

 Games

0.59

Activations Density 0.322%

technical terms related to science or medicine

names of specific places and locations

No Comments

No Known Activations