INDEX

Explanations

symbols and representations related to significant themes and motifs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Jefus

-0.67

 myſelf

-0.65

 Monfieur

-0.65

 houſe

-0.62

__':

-0.60

 Chrift

-0.59

__":

-0.58

 PublicKey

-0.57

moiselle

-0.57

 whoſe

-0.57

POSITIVE LOGITS

 symbolism

0.88

 symbolizes

0.73

 symbol

0.73

 simbol

0.71

Rüyada

0.70

 simbo

0.68

 symbo

0.66

Symbolic

0.65

 symbolize

0.65

 message

0.64

Activations Density 0.118%

symbols and representations related to significant themes and motifs

No Comments

No Known Activations