INDEX

Explanations

personal names and entities in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 itſelf

-1.04

 pleaſure

-0.91

 myſelf

-0.85

 ſmall

-0.77

 Conſ

-0.75

 Monfieur

-0.75

 fhew

-0.74

 ſche

-0.73

 Diſ

-0.71

 ſever

-0.71

POSITIVE LOGITS

 Charles

0.77

("%.

0.74

 Edward

0.73

 George

0.73

PhysRev

0.70

djangoproject

0.70

 Robert

0.70

 Henry

0.69

 William

0.69

Ed

0.68

Activations Density 0.897%

personal names and entities in the text

No Comments

No Known Activations