INDEX

Explanations

timestamps and labels related to file edits or posts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Last" or variations of "last."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

mble

-0.83

mbuds

-0.65

OPLE

-0.64

nai

-0.64

afort

-0.63

apore

-0.62

 Everest

-0.62

qqa

-0.62

 Cornwall

-0.62

rito

-0.60

POSITIVE LOGITS

 Gleaming

0.92

 ditch

0.88

ebin

0.84

 gasp

0.81

fm

0.81

orian

0.76

 week

0.75

 night

0.74

ime

0.74

 rites

0.74

Activations Density 0.057%

timestamps and labels related to file edits or posts

instances of the word "Last" or variations of "last."

No Comments

No Known Activations