INDEX

Explanations

references to physical objects, specifically items like tables

oai_token-act-pair · gpt-3.5-turbo

repeated references to "tables."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

esp

-0.70

eworld

-0.66

cknow

-0.66

trak

-0.65

Film

-0.65

aeper

-0.63

PLIED

-0.63

 Achievement

-0.63

=~=~

-0.63

ship

-0.62

POSITIVE LOGITS

 tables

1.29

poons

1.20

paces

1.04

pace

1.02

 Tables

1.02

hops

0.89

heet

0.87

etting

0.87

hare

0.85

poon

0.85

Activations Density 0.013%

references to physical objects, specifically items like tables

repeated references to "tables."

No Comments

No Known Activations