INDEX

Explanations

references to profiles or profile-related information

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

"profile" and "profiles"

np_acts-logits-general · gemini-2.0-flash

profile

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.79

Bolt

-0.74

__':

-0.71

ptonshire

-0.69

ransition

-0.66

 елның

-0.66

CrossRef

-0.65

lasia

-0.65

 Cranston

-0.64

 Tennant

-0.63

POSITIVE LOGITS

 profiles

1.57

 profile

1.47

 Profiles

1.41

 Profile

1.38

Profiles

1.30

profiles

1.29

 PROFILE

1.28

PROFILE

1.22

profile

1.21

 profiling

1.15

Activations Density 0.107%

references to profiles or profile-related information

"profile" and "profiles"

profile

No Comments

No Known Activations