INDEX

Explanations

structured data or numerical information related to processes or devices

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

PerformLayout

-0.64

enumi

-0.63

‐

-0.63

ﬃ

-0.62

NUMX

-0.61

 مشين

-0.55



-0.54

 ͡°

-0.54

±

-0.52

—“

-0.51

POSITIVE LOGITS

2.85

.(

1.56

'(

1.50

((

1.50

(_

1.49

(-

1.47

?(

1.46

($

1.45

!(

1.45

Activations Density 0.879%

structured data or numerical information related to processes or devices

No Comments

No Known Activations