INDEX

Explanations

phrases related to 'setting' something or establishing a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ValueStyle

-0.67

 ISNI

-0.49

 rozdí

-0.48

 nabíz

-0.47

 změ

-0.45

 příjem

-0.45

 dětí

-0.43

 dům

-0.43

 zmiany

-0.43

 AssemblyCompany

-0.43

POSITIVE LOGITS

set

1.80

 sets

0.96

 ſet

0.86

Set

0.82

 laid

0.72

set

0.71

put

0.67

run

0.66

 plan

0.65

lay

0.65

Activations Density 0.179%

phrases related to 'setting' something or establishing a context

No Comments

No Known Activations