INDEX

Explanations

references to user profiles and profile-related attributes

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

AutoScaleMode

-0.81

 calculées

-0.78

 Cranston

-0.75

__':

-0.73

CrossRef

-0.73

HttpPut

-0.70

Bolt

-0.70

 tóxic

-0.69

(/^

-0.69

 Lessing

-0.68

POSITIVE LOGITS

 profiles

1.72

 profile

1.69

 Profile

1.65

 Profiles

1.56

Profiles

1.51

PROFILE

1.48

 PROFILE

1.47

profiles

1.47

profile

1.41

Profile

1.36

Activations Density 0.042%

references to user profiles and profile-related attributes

No Comments

No Known Activations