INDEX

Explanations

mentions or references to political figures and events

oai_token-act-pair · gpt-3.5-turbo

references to political events and figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Sund

-0.58

reek

-0.53

 Hawks

-0.53

Els

-0.51

ãĥ³ãĤ¸

-0.49

tho

-0.49

Nar

-0.49

 Samar

-0.48

pac

-0.48

oy

-0.48

POSITIVE LOGITS

.''.

1.00

*.

0.89

ãĢĤ

0.89

.''

0.80

.).

0.79

.*

0.78

.(

0.76

.ï¿½

0.75

 attRot

0.73

Activations Density 1.260%

mentions or references to political figures and events

references to political events and figures

No Comments

No Known Activations