INDEX

Explanations

verbs that suggest actions or suggestions of improvement

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

ecuzione

-0.58

 privés

-0.56

جستارهای

-0.56

duma

-0.52

 privée

-0.52

 πρά

-0.51

 orbiting

-0.51

záll

-0.50

 viata

-0.49

openSession

-0.49

POSITIVE LOGITS

parsedMessage

0.94

+#+#

0.85

AsUp

0.83

DoubleQuotes

0.82

kloped

0.81

PyExc

0.76

extAlignment

0.75

ThroughAttribute

0.73

RepeatedField

0.69

TintMode

0.68

Activations Density 0.090%

verbs that suggest actions or suggestions of improvement

No Comments

No Known Activations