INDEX

Explanations

occurrences of punctuation marks and specific formatting characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

*************/

-0.49

-0.44

-0.43

Millan

-0.43

 roce

-0.41

nô

-0.40

 Mund

-0.40

getAttributes

-0.40

 колен

-0.39

ContentAsync

-0.39

POSITIVE LOGITS

ViewFeatures

0.92

SequentialGroup

0.77

Hentet

0.77



0.76

RenderAtEndOf

0.71

qtype

0.71

 sentimenti

0.71

AxisAlignment

0.69

 herself

0.68

abestanden

0.67

Activations Density 0.077%

occurrences of punctuation marks and specific formatting characters

No Comments

No Known Activations