INDEX

Explanations

mentions of individuals and their interactions, particularly in the context of statements or evidence presented

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Dorsey

-0.74

 Franks

-0.74

 Pendleton

-0.72

 Jake

-0.70

 Frank

-0.69

 FRANK

-0.68

 Salam

-0.67

Ros

-0.67

FRANK

-0.66

Ember

-0.66

POSITIVE LOGITS

 Vaughan

0.81

 Leicester

0.68

 Schra

0.68

GTA

0.66

Kuh

0.65

 Schles

0.65

GT

0.65

 Warwick

0.64

 Kidney

0.64

 Shaffer

0.63

Activations Density 1.768%

mentions of individuals and their interactions, particularly in the context of statements or evidence presented

No Comments

No Known Activations