INDEX

Explanations

references to specific software components and their configurations

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

File paths and versions (x64/x86, numbers)

np_acts-logits-general · gemini-2.0-flash

x64 architecture with 64-bit

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

<eos>

-0.57

-0.55

“

-0.54

-0.51

-0.49

-0.48

in

-0.47

so

-0.47

<strong>

-0.47

-0.46

POSITIVE LOGITS

 للمعارف

1.24

RegressionTest

1.08

 greateſt

1.03

 pleaſure

1.01

ⓧ

1.00

 ſche

0.97

########.

0.96

 myſelf

0.96

 Monfieur

0.94

 ſever

0.94

Activations Density 0.928%

references to specific software components and their configurations

File paths and versions (x64/x86, numbers)

x64 architecture with 64-bit

No Comments

No Known Activations

references to specific software components and their configurations

File paths and versions (x64/x86, numbers)

x64 architecture with 64-bit

No Comments

No Known Activations