INDEX

Explanations

words related to explanation and exploration, particularly in academic or analytical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 CreateTagHelper

-1.01

ConstraintMaker

-0.76

fjspx

-0.75

NameInMap

-0.72

 <<<<<<<<<<<<<<

-0.69

featureID

-0.69

hasRole

-0.68

 SEDS

-0.67

 Normdatei

-0.67

 <=",

-0.65

POSITIVE LOGITS

tacular

0.55

 reafon

0.52

Ră

0.52

ation

0.51

 globo

0.51

świet

0.50

ภัย

0.50

losure

0.50

ERI

0.50

 eksp

0.49

Activations Density 0.120%

words related to explanation and exploration, particularly in academic or analytical contexts

No Comments

No Known Activations