INDEX

Explanations

references to legal concepts or terminology

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InSection

-0.79

PerformLayout

-0.77

 Preferencias

-0.76

LookAnd

-0.74

oa̍t

-0.73

#+#

-0.69

ftagPool

-0.69

IVEREF

-0.67

mybatisplus

-0.66

ClientSize

-0.65

POSITIVE LOGITS

 words

3.12

 Words

2.53

words

2.44

Words

2.38

 WORDS

2.35

 palabras

2.00

 word

1.97

WORDS

1.90

 woorden

1.86

 palavras

1.76

Activations Density 0.156%

references to legal concepts or terminology

No Comments

No Known Activations