INDEX

Explanations

names starting with the letters "Ke"

oai_token-act-pair · gemini-2.0-flash

variations of the token 'Ke'

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

Ke

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.77

MockMvc

-0.69

UpInside

-0.68

 surla

-0.67

+][

-0.66

ніципа

-0.66

neous

-0.64

 resourceCulture

-0.64

DebuggerNonUser

-0.64

AddTagHelper

-0.61

POSITIVE LOGITS

irsten

0.43

 kanssa

0.40

po

0.40

 NSCoder

0.40

tinyos

0.39

 cyclisme

0.37

 acogedor

0.36

po

0.36

 gradova

0.36

Rhestr

0.35

Activations Density 0.139%

names starting with the letters "Ke"

variations of the token 'Ke'

Ke

No Comments

No Known Activations