INDEX

Explanations

descriptions of criminal activity in police testimony.

oai_token-act-pair · gemini-2.0-flash

colors or descriptors of substances

np_token-act-pair-logits · gpt-4o-mini

white

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Meksiku

-0.84

setVerticalGroup

-0.70

parsedMessage

-0.65

migrationBuilder

-0.64

BnF

-0.64

BagLayout

-0.62

 دیکھیے

-0.61

 thiệu

-0.60

mă

-0.60

 للاسماء

-0.60

POSITIVE LOGITS

 white

1.05

white

0.87

 green

0.82

 object

0.79

 black

0.76

 substance

0.73

red

0.72

 yellow

0.72

 brown

0.71

 liquid

0.71

Activations Density 2.704%

descriptions of criminal activity in police testimony.

colors or descriptors of substances

white

No Comments

No Known Activations