INDEX

Explanations

programming constructs and syntax specific to image processing or manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 itſelf

-1.11

 myſelf

-1.10

 pleaſure

-0.95

 Monfieur

-0.90

 ſtate

-0.90

 ſeveral

-0.88

 Houſe

-0.87

 chi̍t

-0.84

 uſe

-0.83

 houſe

-0.83

POSITIVE LOGITS

 nargin

1.04

,:);

0.87

(:,

0.86

 varargin

0.81

hObject

0.77

 isempty

0.77

varargin

0.75

matlab

0.74

isempty

0.73

AutoField

0.72

Activations Density 0.939%

programming constructs and syntax specific to image processing or manipulation

No Comments

No Known Activations