INDEX

Explanations

function calls and error logging statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 AssemblyProduct

-0.66

 expression

-0.62

 expressão

-0.61

}{*}{

-0.61

Brainz

-0.59

 initComponents

-0.58

BufferException

-0.57

 AssemblyTitle

-0.57

 архивлан

-0.56

RRect

-0.56

POSITIVE LOGITS

,,,

0.90

,,,,

0.83

!,

0.75

,,

0.75

 kasarigan

0.71

,-,

0.70

 ',',

0.70

``,

0.66

0.64

 "/",

0.64

Activations Density 0.149%

function calls and error logging statements in code

No Comments

No Known Activations