INDEX

Explanations

specific nouns and categories related to various topics such as food, models, discrimination, questions, music, and certifications

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.19

-0.83

-0.80

-0.76

–

-0.70

…

-0.70

glBind

-0.69

...

-0.69

POSITIVE LOGITS

 thut

1.94

aen

1.86

 bandung

1.82

fta

1.81

ftu

1.79

 dises

1.76

 jaya

1.75

 nece

1.74

 affor

1.73

 Minang

1.72

Activations Density 0.153%

specific nouns and categories related to various topics such as food, models, discrimination, questions, music, and certifications

No Comments

No Known Activations