INDEX

Explanations

references to horror and related themes

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

horror stories, films, or tales

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

iqué

-0.59

pse

-0.57

swick

-0.53

⟬

-0.53

PSE

-0.52

 tickle

-0.52

 Sext

-0.52

tse

-0.52

己

-0.52

 Twee

-0.51

POSITIVE LOGITS

 Horror

1.05

horror

1.00

 horror

0.99

Horror

0.99

 horrors

0.74

 Horowitz

0.71

Hor

0.69

 horrified

0.65

 corrupción

0.64

HOR

0.63

Activations Density 0.005%

references to horror and related themes

horror stories, films, or tales

No Comments

No Known Activations