INDEX

Explanations

elements and descriptors that evoke emotional responses or assessments

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

that describe something

np_acts-logits-general · gemini-2.0-flash

describing words

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

SourceChecksum

-0.71

InjectAttribute

-0.55

/-/

-0.54

Buildable

-0.53

 kasarigan

-0.52

GEBURTSDATUM

-0.51

SequentialGroup

-0.51

:+:

-0.50

inaison

-0.50

marty

-0.49

POSITIVE LOGITS

 description

2.19

 describe

2.19

 describing

2.04

 describes

1.98

 descriptions

1.86

description

1.82

describing

1.76

 Description

1.75

 Descri

1.75

 DESCR

1.72

Activations Density 0.321%

elements and descriptors that evoke emotional responses or assessments

that describe something

describing words

No Comments

No Known Activations