INDEX

Explanations

names and terms related to specific geographical locations and people

oai_token-act-pair · gpt-3.5-turbo

words that relate to names or identifiers associated with people or entities

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

 antip

-0.63

 underpin

-0.60

pus

-0.59

bub

-0.58

 mars

-0.58

)=(

-0.57

iasco

-0.56

phe

-0.55

olis

-0.55

çīĪ

-0.55

POSITIVE LOGITS

uthor

0.89

uni

0.79

URI

0.78

´

0.78

»

0.73

ugi

0.72

¦

0.72

¶æ

0.69

 Grip

0.69

jin

0.69

Activations Density 0.120%

names and terms related to specific geographical locations and people

words that relate to names or identifiers associated with people or entities

No Comments

No Known Activations