INDEX

Explanations

words related to functions or methods, especially those indicating appending or ending actions within programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Биография

-0.60

enumii

-0.56

dhury

-0.54

MOP

-0.52

객

-0.51

dataclass

-0.50

enumi

-0.50

majority

-0.50

ณ์

-0.50

 blackout

-0.50

POSITIVE LOGITS

ended

0.96

ender

0.90

ending

0.89

enda

0.72

ENDER

0.69

 Meksiku

0.67

enders

0.63

 مرئيه

0.62

 وتسجيلات

0.60

ends

0.60

Activations Density 0.128%

words related to functions or methods, especially those indicating appending or ending actions within programming contexts

No Comments

No Known Activations