INDEX

Explanations

references to citations or omitted information

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

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

zzar

-0.74

ViewFeatures

-0.71

 Leviathan

-0.68

take

-0.66

Take

-0.63

 Wainwright

-0.62

ResumeLayout

-0.61

 Take

-0.61

kiel

-0.58

race

-0.57

POSITIVE LOGITS

 Cited

1.36

Cited

1.09

CWE

0.91

"}")

0.90

 ujednoznacz

0.88

 NSCoder

0.81

:].

0.79

 مرئيه

0.75

 Bourgoin

0.75

 cheminée

0.74

Activations Density 0.000%

references to citations or omitted information

No Comments

No Known Activations