INDEX

Explanations

verbs and terms related to negative or unpleasant experiences

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

ending in "r" followed by a consonant or "y"

np_acts-logits-general · gemini-2.0-flash

forms words ending in ur/or/ar/ir

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

httphttps

-0.59

ClientSize

-0.59

 civil

-0.54

 Civil

-0.53

Sı

-0.53

ODES

-0.53

Personendaten

-0.53

Références

-0.52

 geti

-0.51

 ISNI

-0.51

POSITIVE LOGITS

ks

0.62

king

0.57

LayoutStyle

0.52

 Forumite

0.49

ching

0.49

pholes

0.48

entibus

0.48

ts

0.47

ksh

0.47

ky

0.46

Activations Density 0.260%

verbs and terms related to negative or unpleasant experiences

ending in "r" followed by a consonant or "y"

forms words ending in ur/or/ar/ir

No Comments

No Known Activations