INDEX

Explanations

positive comments and feedback

oai_token-act-pair · gemini-2.0-flash

technical terms related to programming or software development

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

positive reviews and opinions

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

Negative Logits

 发表于

-0.58

principalColumn

-0.53

alip

-0.53

 Ouvrez

-0.53

 Neutron

-0.51

supra

-0.51

isempty

-0.51

QRST

-0.50

 paramInt

-0.49

lastIndexOf

-0.49

POSITIVE LOGITS

complexContent

0.84

writeFieldEnd

0.76

ReusableCell

0.72

oredCriteria

0.66

MigrationBuilder

0.65

OpenHelper

0.61

ContentAsync

0.57

ThroughAttribute

0.56

contentLoaded

0.52

RectangleBorder

0.52

Activations Density 0.610%

positive comments and feedback

technical terms related to programming or software development

positive reviews and opinions

No Known Activations