INDEX

Explanations

definitions and descriptions of concepts

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

Comes after a period

np_acts-logits-general · gemini-2.0-flash

definitions and typical occurrences

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

ècie

-0.72

SequentialGroup

-0.72

 propOrder

-0.69

ResumeLayout

-0.67

__((

-0.66

новниш

-0.66

audrait

-0.65

wapV

-0.64

 <<<<<<<<<<<<<<

-0.63

HttpDelete

-0.63

POSITIVE LOGITS

Generally

0.84

Typically

0.84

Usually

0.84

 commonly

0.83

 usually

0.82

 Generally

0.79

usually

0.78

 Traditionally

0.77

typically

0.77

 Usually

0.76

Activations Density 0.599%

definitions and descriptions of concepts

Comes after a period

definitions and typical occurrences

No Comments

No Known Activations