INDEX

Explanations

text snippets in various languages, likely due to unique characters or character combinations

oai_token-act-pair · gpt-3.5-turbo

special characters or symbols 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Lyons

-0.95

 Parsons

-0.95

 brethren

-0.78

 Mason

-0.77

 Goddard

-0.77

iggins

-0.71

Barn

-0.71

Que

-0.70

 McGee

-0.70

annel

-0.68

POSITIVE LOGITS

å

3.18

é

3.01

ç

2.95

è

2.94

æ

2.94

 ãĥ

2.57

 ãĤ

2.49

 ãģ

2.44

 å¤

2.37

 æľ

2.34

Activations Density 0.036%

text snippets in various languages, likely due to unique characters or character combinations

special characters or symbols in the text

No Comments

No Known Activations