INDEX

Explanations

references to labels and session management in a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-1.05

 myſelf

-0.97

 Majefty

-0.96

 purpoſe

-0.95

 becauſe

-0.92

 cauſe

-0.92

 Anſ

-0.90

 juſt

-0.89

 reaſon

-0.88

 themſelves

-0.88

POSITIVE LOGITS

 sessions

0.98

 label

0.98

 labels

0.93

session

0.86

 Label

0.86

 session

0.85

 Sessions

0.83

sessions

0.79

SESSION

0.77

 Labels

0.77

Activations Density 0.124%

references to labels and session management in a coding context

No Comments

No Known Activations