INDEX

Explanations

web links or locations mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

references to a location for further information or content

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

 uptake

-0.62

 diapers

-0.60

 ceilings

-0.60

 tongues

-0.59

 Labrador

-0.59

 judgement

-0.58

 concentration

-0.58

iven

-0.57

 havoc

-0.56

 consequence

-0.56

POSITIVE LOGITS

tical

1.34

abouts

1.29

tics

1.25

tic

1.05

 âĸº

0.81

 https

0.81

with

0.80

 http

0.76

endix

0.75

ina

0.73

Activations Density 0.041%

web links or locations mentioned in the text

references to a location for further information or content

No Comments

No Known Activations