INDEX

Explanations

proper nouns, particularly names of individuals

oai_token-act-pair · gpt-3.5-turbo

prominent names and terms related to notable individuals or places

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

haps

-0.70

ngth

-0.68

racuse

-0.61

 scrimmage

-0.59

ruary

-0.56

enza

-0.55

 ancest

-0.55

udic

-0.54

orescent

-0.54

xus

-0.53

POSITIVE LOGITS

INE

0.62

__

0.57

EMENT

0.57

ines

0.56

ined

0.54

eers

0.53

________

0.52

âĸĪâĸĪ

0.52

organic

0.51

aws

0.51

Activations Density 0.235%

proper nouns, particularly names of individuals

prominent names and terms related to notable individuals or places

No Comments

No Known Activations