INDEX

Explanations

references to specific individuals, particularly those involved in scientific or medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-1.48

-1.35

-1.29

-1.16

-1.14

-1.13

-1.12

-1.11

POSITIVE LOGITS

 myſelf

1.86

 themſelves

1.65

BibitemShut

1.63

 Monfieur

1.59

 purpoſe

1.55

 itſelf

1.55

 pleaſure

1.53

 ſeveral

1.52

 ་་

1.52

 reaſon

1.52

Activations Density 0.380%

references to specific individuals, particularly those involved in scientific or medical contexts

No Comments

No Known Activations