INDEX

Explanations

the last names of political figures

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to political figures and organizations

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

 cannabin

-0.67

atern

-0.66

nect

-0.64

NAS

-0.63

alog

-0.62

olicy

-0.62

asonic

-0.60

 awarding

-0.59

angible

-0.59

 administering

-0.58

POSITIVE LOGITS

tsky

0.90

ttes

0.77

geoning

0.75

ez

0.75

yre

0.74

vez

0.73

gence

0.73

dit

0.72

illance

0.72

tsy

0.72

Activations Density 0.054%

the last names of political figures

proper nouns related to political figures and organizations

No Comments

No Known Activations