INDEX

Explanations

occurrences of modal verbs and verbs indicating actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

Personendaten

-0.96

 EconPapers

-0.80

MigrationBuilder

-0.80

 ExecuteAsync

-0.79

ThroughAttribute

-0.74

UnusedPrivate

-0.71

 defaultstate

-0.71

AccessorTable

-0.71

aarrggbb

-0.70

 ImportError

-0.69

POSITIVE LOGITS

ikin

0.53

 appelez

0.51

 шар

0.49

HasAnnotation

0.49

0.48

 candidate

0.48

me

0.45

her

0.45

 recommandée

0.45

transQ

0.44

Activations Density 0.893%

occurrences of modal verbs and verbs indicating actions or processes

No Comments

No Known Activations