INDEX

Explanations

names of locations and devices

oai_token-act-pair · gpt-3.5-turbo

specific names, titles, or terms related to medical or technical contexts

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

flags

-0.58

lov

-0.58

ova

-0.56

anas

-0.56

eper

-0.54

vari

-0.53

ccording

-0.53

userc

-0.53

 citiz

-0.52

afety

-0.52

POSITIVE LOGITS

tein

0.71

ktop

0.62

 Sachs

0.56

Das

0.53

shire

0.51

Cly

0.50

RSA

0.50

Uncommon

0.50

 Hubbard

0.49

 McKay

0.48

Activations Density 1.256%

names of locations and devices

specific names, titles, or terms related to medical or technical contexts

No Comments

No Known Activations