INDEX

Explanations

positive adjectives expressing approval or praise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 getItemId

-0.63

/*++

-0.61

DockStyle

-0.58

 &___

-0.57

 >=",

-0.55

 gyhoeddwyd

-0.55

PhysRevLett

-0.55

 klokken

-0.55

 становника

-0.53

 suivantes

-0.53

POSITIVE LOGITS

job

1.10

 idea

0.96

 choice

0.85

Job

0.83

 work

0.79

job

0.76

 initiative

0.76

JOB

0.75

 concept

0.72

 decision

0.72

Activations Density 0.067%

positive adjectives expressing approval or praise

No Comments

No Known Activations