INDEX

Explanations

code snippets and syntax related to programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

TagMode

-0.53

The

-0.51

 Although

-0.50

---*/

-0.50

 Whether

-0.48

If

-0.48

-0.47

An

-0.47

雖然

-0.47

POSITIVE LOGITS

ViewFeatures

0.88

AutoScaleMode

0.78

principalTable

0.73

orsese

0.72

省市镇

0.72

Efq

0.71

dafx

0.69

__':

0.67

ItemBackground

0.67

 Theſe

0.67

Activations Density 0.830%

code snippets and syntax related to programming constructs

No Comments

No Known Activations