INDEX

Explanations

Twitter handles

oai_token-act-pair · gpt-3.5-turbo

Twitter handles and user mentions in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Association

-0.92

 Parish

-0.87

 Evaluation

-0.82

 Reconstruction

-0.81

Act

-0.80

CSI

-0.80

 Penal

-0.79

 Transparency

-0.78

 Rend

-0.78

 Advisory

-0.78

POSITIVE LOGITS

john

1.33

mma

1.33

mad

1.32

ngth

1.32

christ

1.31

phil

1.30

brown

1.30

wild

1.29

podcast

1.29

kid

1.28

Activations Density 0.178%

Twitter handles

Twitter handles and user mentions in the text

No Comments

No Known Activations