INDEX

Explanations

programming structures and syntax

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

Tokens after certain letters or symbols

np_acts-logits-general · gemini-2.0-flash

WT prefixes, wounded, wafer

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

SequentialGroup

-0.64

 незавершена

-0.61

 jsPsych

-0.59

="@+

-0.57

MLLoader

-0.55

enumi

-0.53

MergeFrom

-0.53

principalTable

-0.52

Autoritní

-0.52

CTV

-0.52

POSITIVE LOGITS

WT

1.22

WC

1.20

WB

1.20

WA

1.19

WR

1.19

WS

1.18

WP

1.12

WL

1.12

WI

1.11

Wa

1.10

Activations Density 1.041%

programming structures and syntax

Tokens after certain letters or symbols

WT prefixes, wounded, wafer

No Comments

No Known Activations