INDEX

Explanations

names or partial names of entities or individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns or names associated with legal and personal contexts

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

 meas

-0.85

ABE

-0.80

Þ

-0.77

Aw

-0.75

Ub

-0.74

AW

-0.74

........................

-0.74

AV

-0.73

 Astro

-0.73

 simul

-0.72

POSITIVE LOGITS

len

1.51

1.39

lin

1.38

lan

1.38

lins

1.37

lem

1.36

li

1.36

ler

1.32

lers

1.30

lÃ©

1.30

Activations Density 0.186%

names or partial names of entities or individuals

proper nouns or names associated with legal and personal contexts

No Comments

No Known Activations