INDEX

Explanations

terms related to objectivity and evidence in various contexts

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

ending in common suffixes

np_acts-logits-general · gemini-2.0-flash

abstract qualities and states

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

хьтан

-0.63

úgó

-0.63

FORME

-0.60

ôles

-0.59

떻

-0.57

volent

-0.57

reathable

-0.57

ionale

-0.56

 Hygien

-0.56

AZIONI

-0.55

POSITIVE LOGITS

fulness

0.95

ness

0.93

iness

0.89

ishness

0.87

leness

0.87

lessness

0.87

eness

0.87

veness

0.83

ality

0.80

reness

0.79

Activations Density 0.356%

terms related to objectivity and evidence in various contexts

ending in common suffixes

abstract qualities and states

No Comments

No Known Activations