INDEX

Explanations

temporal or chronological indicators in 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

 onCancelled

-0.52

etree

-0.40

bant

-0.40

 confortável

-0.39

Leaky

-0.39

et

-0.38

Bole

-0.35

op

-0.34

both

-0.34

 consolidated

-0.34

POSITIVE LOGITS

AnchorStyles

0.96

ConstraintMaker

0.96

LookAnd

0.90

ScopeManager

0.88

oneofs

0.80

rungsseite

0.77

ValueStyle

0.77

findpost

0.77

+#+#

0.74

principalTable

0.73

Activations Density 0.096%

temporal or chronological indicators in the text

No Comments

No Known Activations