INDEX

Explanations

terms related to user profiles

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

mentions of “profile” and closely related profile-page or profile-metadata terms, especially in account, biographical, or listing contexts.

oai_token-act-pair · gpt-5 Triggered by @liuliujiujiu05

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

AutoScaleMode

-0.89

principalColumn

-0.77

 calculées

-0.74

__':

-0.71

 Cranston

-0.70

(/^

-0.68

lasia

-0.68

CrossRef

-0.68

Bolt

-0.68

 getStart

-0.67

POSITIVE LOGITS

 profiles

1.76

 profile

1.72

 Profile

1.68

 Profiles

1.59

Profiles

1.54

PROFILE

1.52

 PROFILE

1.49

profiles

1.48

profile

1.47

Profile

1.40

Activations Density 0.051%

terms related to user profiles

mentions of “profile” and closely related profile-page or profile-metadata terms, especially in account, biographical, or listing contexts.

No Comments

No Known Activations