INDEX

Explanations

references to geographical locations and names associated with specific historical or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Rockets

-0.94

 Rask

-0.94

 Rott

-0.80

 Rasmussen

-0.79

 Rhod

-0.78

 Reece

-0.77

RB

-0.77

RSD

-0.77

RCC

-0.76

RDC

-0.76

POSITIVE LOGITS

 Chomsky

0.74

 '\\;'

0.73

__":

0.72

 AssemblyCulture

0.72

ignet

0.69

IMPORTED

0.67

팽

0.67

Mojo

0.65

ocino

0.65

 Spie

0.65

Activations Density 1.267%

references to geographical locations and names associated with specific historical or scientific contexts

No Comments

No Known Activations