INDEX

Explanations

proper nouns related to individuals

oai_token-act-pair · gpt-3.5-turbo

the name "Hutch" and its variations in the context of individuals or entities associated with it

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

ãĥ©ãĥ³

-0.85

forth

-0.82

Ton

-0.81

jug

-0.69

prim

-0.68

ethnic

-0.66

xual

-0.66

hair

-0.65

ergic

-0.65

Lear

-0.65

POSITIVE LOGITS

sonian

1.24

rosis

0.84

doms

0.79

rike

0.71

nesday

0.71

 Cheong

0.69

riad

0.68

ierrez

0.67

owship

0.67

 Hutchinson

0.65

Activations Density 0.059%

proper nouns related to individuals

the name "Hutch" and its variations in the context of individuals or entities associated with it

No Comments

No Known Activations