INDEX

Explanations

questions starting with "How"

oai_token-act-pair · gpt-3.5-turbo

questions that begin with "How."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

goers

-0.66

ultimate

-0.64

ptions

-0.62

outer

-0.60

 Feld

-0.58

 hereafter

-0.57

article

-0.57

 grounds

-0.57

piece

-0.56

room

-0.55

POSITIVE LOGITS

soever

1.14

ever

1.10

ells

1.04

beit

1.01

ling

0.94

itzer

0.91

dy

0.88

 dare

0.82

leep

0.80

 much

0.80

Activations Density 0.076%

questions starting with "How"

questions that begin with "How."

No Comments

No Known Activations