INDEX

Explanations

the token "exp" in code snippets

oai_token-act-pair · gemini-2.0-flash

exp

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.79

-0.71

 '\\;'

-0.69

-0.67

 public

-0.67

 ModelExpression

-0.63

KURZBESCHREIBUNG

-0.63

verwijspagina

-0.61

 cont

-0.61

DockStyle

-0.61

POSITIVE LOGITS

 sauvages

1.09

 mariée

1.05

 rayures

1.04

 Theſe

1.03

 vectorielles

1.03

 debout

1.02

 abstrait

1.01

 avoient

1.00

 quelcon

0.98

 varandra

0.98

Activations Density 0.876%

the token "exp" in code snippets

exp

No Comments

No Known Activations