INDEX

Explanations

expressions of enjoyment or pleasure

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

enjoy followed by possessive noun

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

MENAFN

-0.64

TableBody

-0.58



-0.57

ClientSize

-0.57

 Audiodateien

-0.57

참고

-0.57

stdc

-0.52

\{\\

-0.52

ineno

-0.50

 utafitiHapana

-0.50

POSITIVE LOGITS

 themselves

1.09

 itself

1.08

 herself

1.07

 yourself

0.97

 himself

0.96

 ourselves

0.91

 oneself

0.82

 Himself

0.81

themselves

0.80

itself

0.79

Activations Density 0.006%

expressions of enjoyment or pleasure

enjoy followed by possessive noun

No Comments

No Known Activations