INDEX

Explanations

various instances of the word "type" and its variations in different contexts

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

 Anſ

-0.88

 nicio

-0.84

 HomeComponent

-0.83

 Audiodateien

-0.83

UnsafeEnabled

-0.81

 Monfieur

-0.80

 Becken

-0.80

sizeCache

-0.80

 ſee

-0.79

 AppBar

-0.79

POSITIVE LOGITS

 Type

1.48

 TYPE

1.46

 types

1.37

 type

1.31

 getType

1.27

TYPE

1.25

types

1.25

Type

1.21

type

1.20

 Types

1.17

Activations Density 0.220%

various instances of the word "type" and its variations in different contexts

No Comments

No Known Activations