INDEX

Explanations

references to exceptions or rules within a context

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

exceptions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

-0.46

“

-0.40

 managerial

-0.38

 Managerial

-0.38

Board

-0.36

“

-0.36

ar

-0.36

Management

-0.36

-0.35

POSITIVE LOGITS

 exceptions

1.16

 exception

1.09

 Exceptions

1.03

 Ausnahme

0.90

 excepción

0.89

 Exception

0.89

例外

0.80

StoryboardSegue

0.79

Exceptions

0.79

 excep

0.77

Activations Density 0.016%

references to exceptions or rules within a context

exceptions

No Comments

No Known Activations