INDEX

Explanations

references to problem-solving and issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

AnchorStyles

-0.82

 CURLOPT

-0.82

 تضيفلها

-0.81

 estatales

-0.79

 définiti

-0.77

 prouver

-0.77

 tawny

-0.76

 recevez

-0.73

 promouvoir

-0.73

 gratuitas

-0.72

POSITIVE LOGITS

 problems

1.73

 problem

1.63

 Problems

1.54

 Problem

1.50

 PROBLEM

1.42

Problems

1.41

problems

1.37

PROBLEM

1.35

Problem

1.31

problem

1.30

Activations Density 0.080%

references to problem-solving and issues

No Comments

No Known Activations