INDEX

Explanations

references to artists and exhibitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.74

 NSCoder

-0.74

entile

-0.72

 pleaſure

-0.71

 Conſ

-0.71

ukone

-0.71

 myſelf

-0.69

 Theſe

-0.68

 Diſ

-0.67

 Église

-0.67

POSITIVE LOGITS

 together

0.74

 participated

0.73

together

0.66

Together

0.60

 participate

0.59

 Together

0.59

 belonged

0.59

«

0.58

TagHelper

0.58

 participates

0.58

Activations Density 0.473%

references to artists and exhibitions

No Comments

No Known Activations