INDEX

Explanations

phrases related to weapons and their capabilities

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

 يتيمه

-0.56

 representa

-0.50

rufe

-0.47

Sce

-0.47

rvats

-0.46

่ะ

-0.46

 TestBed

-0.44

ąz

-0.44

={`

-0.44

ostomy

-0.44

POSITIVE LOGITS

RectangleBorder

0.78

顺便

0.78

writeFieldEnd

0.65

 incidentally

0.65

 zugleich

0.64

ModelAdmin

0.64

FormTagHelper

0.62

addCriterion

0.59

 incidental

0.59

ついでに

0.59

Activations Density 0.294%

phrases related to weapons and their capabilities

No Comments

No Known Activations