INDEX

Explanations

mentions of academic studies and reports

oai_token-act-pair · gpt-3.5-turbo

references to research studies and publications

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

asus

-0.69

something

-0.64

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.63

 Sabha

-0.62

 Alexandria

-0.60

 predicament

-0.58

 Rutherford

-0.58

 Asgard

-0.58

mma

-0.58

 Revival

-0.57

POSITIVE LOGITS

uggest

1.47

hips

1.06

hops

1.05

hare

0.99

creen

0.98

mith

0.98

poons

0.95

 indicate

0.93

chool

0.93

amples

0.93

Activations Density 0.328%

mentions of academic studies and reports

references to research studies and publications

No Comments

No Known Activations