INDEX

Explanations

references to "butter" and "Pres" (presumably relating to a specific president or presidential context)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

énario

-0.78

GOTREF

-0.70

MLLoader

-0.64

PyExc

-0.62

ViewImports

-0.61

DebuggerNonUser

-0.59

ρη

-0.58

 AsyncTask

-0.57

 Weldon

-0.57

TabIndex

-0.57

POSITIVE LOGITS

 butter

1.63

 Butter

1.52

butter

1.49

 BUTTER

1.43

Butter

1.41

bu

0.93

Butt

0.92

 pres

0.89

butt

0.88

but

0.82

Activations Density 0.087%

references to "butter" and "Pres" (presumably relating to a specific president or presidential context)

No Comments

No Known Activations

references to "butter" and "Pres" (presumably relating to a specific president or presidential context)

No Comments

No Known Activations