INDEX

Explanations

questions or queries that prompt elaboration or clarification

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

RTEE

-0.58

SqlSession

-0.57

TagHelpers

-0.56

jsonwebtoken

-0.56

jsonPath

-0.56

ResumeLayout

-0.56

PhysRevLett

-0.55

 nawr

-0.55

/\.

-0.54

 समीक्षक

-0.54

POSITIVE LOGITS

]));

0.67

 really

0.64

 truly

0.63

 better

0.59

]),

0.56

Really

0.54

What

0.53

]){

0.53

́ng

0.52

 verdaderamente

0.51

Activations Density 0.114%

questions or queries that prompt elaboration or clarification

No Comments

No Known Activations