INDEX

Explanations

proper nouns related to historical or political figures

oai_token-act-pair · gpt-3.5-turbo

names of prominent individuals, particularly those with the name "Caesar" or related to historical and contemporary figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

pring

-0.89

ochond

-0.82

rike

-0.81

caster

-0.80

tip

-0.79

ritch

-0.79

WARD

-0.79

rien

-0.78

roe

-0.78

ringe

-0.77

POSITIVE LOGITS

esar

1.05

 Clown

1.04

 Augustus

0.82

 Caesar

0.79

 Chavez

0.75

 Ventura

0.74

 Flags

0.74

 Brut

0.74

 Reaper

0.71

Nig

0.70

Activations Density 0.033%

proper nouns related to historical or political figures

names of prominent individuals, particularly those with the name "Caesar" or related to historical and contemporary figures

No Comments

No Known Activations