INDEX

Explanations

instances of dialogue or speech actions within the text

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 poffible

-0.90

 ſche

-0.88

 Roskov

-0.86

 Forumite

-0.84

Efq

-0.84

ſelves

-0.83

 Anſ

-0.83

 Theſe

-0.82

MessageOf

-0.82

 Majefty

-0.82

POSITIVE LOGITS

0.54

and

0.52

0.48

complexContent

0.45

ia

0.44

<eos>

0.43

El

0.43

author

0.43

velse

0.43

精

0.42

Activations Density 0.004%

instances of dialogue or speech actions within the text

No Comments

No Known Activations

instances of dialogue or speech actions within the text

No Comments

No Known Activations