INDEX

Explanations

references to undefined or unspecified entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 doInBackground

-0.85

AsUp

-0.82

__':

-0.75

 gynhyrchwyd

-0.75

__":

-0.71

NKC

-0.69

iciaries

-0.68

 Shakspeare

-0.67

 betweenstory

-0.66

strix

-0.65

POSITIVE LOGITS

uns

0.97

uns

0.86

Uns

0.80

Uns

0.72

GEBURTSDATUM

0.59

 mountains

0.55

 poster

0.55

 Jennifer

0.54

 Sarah

0.53

Jennifer

0.52

Activations Density 0.036%

references to undefined or unspecified entities

No Comments

No Known Activations