INDEX

Explanations

terms related to recognition and understanding

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

Еще

-1.14

 Ее

-1.14

Theater

-1.14

 theater

-1.13

 tumors

-1.10

ighborhood

-1.09

ighbor

-1.07

modeling

-1.06

neighbors

-1.06

 theaters

-1.05

POSITIVE LOGITS

şi

1.75

Ещё

1.72

 organisations

1.68

 generalised

1.66

 utilisation

1.64

Colours

1.63

 organisational

1.63

Şi

1.60

 programmes

1.60

 characterised

1.59

Activations Density 0.313%

terms related to recognition and understanding

No Comments

No Known Activations