INDEX

Explanations

terms related to modification and alteration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

antd

-0.65

</h1>

-0.61

routeProvider

-0.60

dymyr

-0.58

 menilai

-0.57

cupa

-0.53

ufel

-0.53

 dikel

-0.52

</b>

-0.52

@$

-0.50

POSITIVE LOGITS

 modification

1.74

 modifying

1.72

 modif

1.72

 modifications

1.67

 modify

1.66

 Modify

1.62

 modifies

1.60

 Modif

1.60

 Modification

1.60

 modifi

1.57

Activations Density 0.144%

terms related to modification and alteration

No Comments

No Known Activations