INDEX

Explanations

mentions of winning or achieving success in competitions or games

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate completeness or totality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

grad

-0.68

aminer

-0.56

 EVERY

-0.56

stone

-0.56

robe

-0.56

 Malf

-0.55

lav

-0.55

 sometimes

-0.54

lad

-0.52

plin

-0.51

POSITIVE LOGITS

ocating

1.04

usions

0.97

uding

0.94

 three

0.92

igator

0.92

udes

0.89

ocation

0.88

 four

0.88

ogene

0.88

ocations

0.84

Activations Density 0.106%

mentions of winning or achieving success in competitions or games

phrases that indicate completeness or totality

No Comments

No Known Activations