INDEX

Explanations

method calls related to converting objects to strings or JSON format

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

not

-0.61

-0.60

nati

-0.59

el

-0.58

la

-0.58

mandu

-0.58

le

-0.58

co

-0.57

-0.56

ply

-0.55

POSITIVE LOGITS

toString

1.40

 toString

1.35

ToString

1.07

 itſelf

1.03

 ToString

1.02

 GenerationType

1.01

InputBorder

0.95

 Monfieur

0.93

HasBeenSet

0.91

 utafitiHapana

0.91

Activations Density 0.023%

method calls related to converting objects to strings or JSON format

No Comments

No Known Activations