INDEX

Explanations

specific names and references to entities or places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 auffi

-0.67

ſelf

-0.66

 purpoſe

-0.66

 ſta

-0.61

\{\\

-0.58

 ſtre

-0.58

 themſelves

-0.57

 AssemblyTitle

-0.56

 themselves

-0.56

 revanche

-0.56

POSITIVE LOGITS

BASELINE

0.54

Getenv

0.53

mergeFrom

0.53

ArgsConstructor

0.53

ագրություններ

0.50

fromnode

0.47

gmd

0.46

 satisfaire

0.44

Bronnen

0.43

Życiorys

0.42

Activations Density 0.366%

specific names and references to entities or places

No Comments

No Known Activations