INDEX

Explanations

terms related to inclusion and additional components or factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_mlp_out

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

 myſelf

-0.98

 Jefus

-0.94

 doubtnut

-0.93

Efq

-0.91

 ARXIV

-0.89

 itſelf

-0.88

 auffi

-0.88

 himſelf

-0.84

tvguidetime

-0.81

 BRARY

-0.79

POSITIVE LOGITS

As

0.69

↵↵

0.69

↵

0.69

It

0.65

So

0.60

0.59

TagMode

0.59

You

0.57

Activations Density 0.083%

terms related to inclusion and additional components or factors

No Comments

No Known Activations