INDEX

Explanations

references to funding and grants for projects

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

 autobiography

-0.52

 Autobiography

-0.51

FunctionFlags

-0.47

onOptions

-0.46

itness

-0.44

évaluateur

-0.44

 cartaz

-0.43

AccessorTable

-0.43

 mutiny

-0.43

Παραπομπές

-0.43

POSITIVE LOGITS

 grant

2.12

 grants

1.90

 funding

1.87

grant

1.73

 Grant

1.59

grants

1.56

 Grants

1.54

Grant

1.53

funding

1.49

Grants

1.49

Activations Density 0.344%

references to funding and grants for projects

No Comments

No Known Activations