INDEX

Explanations

programming-related commands or functions in the code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 aggiunto

-0.61

addEdge

-0.50

fillText

-0.46

)++;

-0.46

ctibles

-0.46

 broadened

-0.46

ILED

-0.46

 expanded

-0.44

stdc

-0.44

osex

-0.44

POSITIVE LOGITS

 reverse

0.90

 undoing

0.89

reverse

0.82

 reversing

0.81

 undo

0.77

AccessorTable

0.77

 remove

0.76

 reversal

0.75

 removing

0.75

 Undo

0.75

Activations Density 0.491%

programming-related commands or functions in the code

No Comments

No Known Activations