INDEX

Explanations

terms related to genetic variations and their effects on physical traits or conditions

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

say words ending with "ly"

np_max-act-logits · gpt-4.1-mini-2025-04-14 Triggered by @arientigiacomo2003

say "ly" ending

np_max-act-logits · gpt-4o-mini Triggered by @arientigiacomo2003

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Л

-0.81

LL

-0.81

Ll

-0.76

LI

-0.72

LM

-0.66

RL

-0.66

 Ли

-0.65

LH

-0.65

Լ

-0.64

LJ

-0.63

POSITIVE LOGITS

le

0.92

led

0.88

la

0.83

let

0.82

les

0.76

late

0.75

los

0.72

las

0.72

leta

0.71

len

0.71

Activations Density 3.299%

terms related to genetic variations and their effects on physical traits or conditions

say words ending with "ly"

say "ly" ending

No Comments

No Known Activations