INDEX

Explanations

countries or geographic locations

oai_token-act-pair · gpt-3.5-turbo

mentions of specific countries, particularly Belarus and Azerbaijan

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

perse

-0.79

vantage

-0.78

ORGE

-0.74

latable

-0.72

athed

-0.71

abolic

-0.70

achers

-0.70

ciation

-0.70

nery

-0.70

Kin

-0.68

POSITIVE LOGITS

insk

0.87

 Bots

0.76

 Belarus

0.74

 pupp

0.69

 resid

0.68

 capit

0.67

 resp

0.67

kers

0.65

âĸĪ

0.64

ansas

0.63

Activations Density 0.023%

countries or geographic locations

mentions of specific countries, particularly Belarus and Azerbaijan

No Comments

No Known Activations