INDEX

Explanations

dialogue or speech markers, indicating quotes or statements made by characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Мексичка

-0.80

Efq

-0.77

=$?

-0.75

tvguidetime

-0.74

 Majefty

-0.72

ſelves

-0.68

 houſe

-0.67

reportWebVitals

-0.66

Hochspringen

-0.65

 Roskov

-0.64

POSITIVE LOGITS

0.64

Hozzáférés

0.59

my

0.57

0.56

 mergeFrom

0.55

ध

0.52

My

0.52

modb

0.52

estay

0.51

 zwar

0.51

Activations Density 0.075%

dialogue or speech markers, indicating quotes or statements made by characters

No Comments

No Known Activations