INDEX

Explanations

programming constructs or code-related elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Wong

-0.51

obrá

-0.49

vod

-0.49

MessageInfo

-0.48

üyor

-0.47

 pitié

-0.46

 getItemId

-0.46

 CURLOPT

-0.45

 health

-0.45

絵

-0.45

POSITIVE LOGITS

 StringBuilder

1.05

ResumeLayout

0.89

IsMutable

0.84

 StringBuffer

0.84

BeginContext

0.82

 Bioaccumulative

0.79

StandardCharsets

0.76

ConstraintMaker

0.76

RenderAtEndOf

0.73

fromCharCode

0.73

Activations Density 0.016%

programming constructs or code-related elements

No Comments

No Known Activations