INDEX

Explanations

terms related to personal aspects and situations

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

following "personal"

np_acts-logits-general · gemini-2.0-flash

personal followed by something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ImageContext

-0.64

URLException

-0.61

 precisamente

-0.60

enumii

-0.57

devamını

-0.56

asticity

-0.55

 précisément

-0.55

 représ

-0.53



-0.52

ladel

-0.52

POSITIVE LOGITS

 Personal

0.93

 personal

0.84

Personal

0.82

PERSONAL

0.78

 PERSONAL

0.75

personal

0.69

ersonal

0.69

 prywat

0.64

+/**

0.60

 persönliche

0.58

Activations Density 0.076%

terms related to personal aspects and situations

following "personal"

personal followed by something

No Comments

No Known Activations