INDEX

Explanations

people or entities related to specific historical or political events

oai_token-act-pair · gpt-3.5-turbo

references to different historical eras

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

sie

-0.94

 mathemat

-0.87

olulu

-0.86

cards

-0.81

eneg

-0.80

lasses

-0.80

rament

-0.79

ers

-0.79

doms

-0.77

inburgh

-0.76

POSITIVE LOGITS

BILITY

0.80

ffiti

0.75

Å

0.71

Äĩ

0.68

interstitial

0.68

 Scotia

0.67

ULT

0.65

jc

0.65

zza

0.65

ption

0.64

Activations Density 0.014%

people or entities related to specific historical or political events

references to different historical eras

No Comments

No Known Activations