INDEX

Explanations

references to characters from books or shows

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

migrationBuilder

-0.81

 bezeichneter

-0.71

Waga

-0.64

PerformLayout

-0.62

Mutagenicity

-0.61

pulumi

-0.59

 pulumi

-0.59

 FormBuilder

-0.58

 Iroquois

-0.58

exponential

-0.58

POSITIVE LOGITS

HBO

0.82

 Targ

0.75

HBO

0.75

 Game

0.73

enerys

0.73

Билгалдахарш

0.71

 Wester

0.69

 Thrones

0.69

Game

0.67

 Stark

0.66

Activations Density 0.038%

references to characters from books or shows

No Comments

No Known Activations