INDEX

Explanations

specific technical specifications or model names related to devices

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

ScopeManager

-0.95

AccessorTable

-0.95

)':

-0.89

TypedDataSet

-0.87

}</

-0.86

)";

-0.85

RenderAtEndOf

-0.85

 Signalez

-0.84

IsContent

-0.84

TagHelper

-0.83

POSITIVE LOGITS

Impl

0.58

III

0.56

 Plus

0.56

Jr

0.56

II

0.56

0.54

plus

0.52

 lite

0.49

Main

0.47

Activations Density 0.917%

specific technical specifications or model names related to devices

No Comments

No Known Activations