INDEX

Explanations

technical terms related to programming and syntax errors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

principalColumn

-0.55

_));

-0.54

omitempty

-0.50

tvguidetime

-0.50

clerview

-0.50

 istitu

-0.50

IContainer

-0.50

 geladeira

-0.50

čku

-0.49

kiye

-0.49

POSITIVE LOGITS

 code

0.64

iastes

0.61

 programming

0.60

íritu

0.55

 ProtoMessage

0.54

RenderAtEndOf

0.54

testens

0.53

letoe

0.53

ANTLR

0.53

errHandler

0.53

Activations Density 0.849%

technical terms related to programming and syntax errors

No Comments

No Known Activations