INDEX

Explanations

phrases related to specific processes or sequences of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Cæsar

-0.72

 Shaksp

-0.66

gants

-0.66

eseorang

-0.65

accesso

-0.64

foro

-0.61

NullException

-0.60

cellular

-0.60

 automatiques

-0.60

 spørgsmål

-0.59

POSITIVE LOGITS

 process

0.79

 dabei

0.79

脚注の使い方

0.73

Dabei

0.72

 course

0.70

 along

0.70

 процессе

0.69

 Dabei

0.69

 proses

0.69

Along

0.67

Activations Density 0.175%

phrases related to specific processes or sequences of events

No Comments

No Known Activations