INDEX

Explanations

programmatic constructs related to function definitions and control flow 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 @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Reſ

-0.77

 pleaſure

-0.74

Autoritní

-0.74

elemField

-0.68

Eſ

-0.68

 myſelf

-0.67

 Diſ

-0.67

 themſelves

-0.66

 purpoſe

-0.66

enumi

-0.65

POSITIVE LOGITS

Max

0.64

preparation

0.63

installation

0.58

reception

0.57

Num

0.57

Top

0.57

Obj

0.56

transmission

0.55

establishment

0.55

 Date

0.55

Activations Density 0.280%

programmatic constructs related to function definitions and control flow in code

No Comments

No Known Activations