INDEX

Explanations

occurrences of the "@" symbol, indicating mentions or tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

кла

-0.51

 переписи

-0.48

 Anything

-0.46

Anything

-0.46

 proceder

-0.46

 sexuales

-0.45

 anything

-0.45

 such

-0.44

ChangeEvent

-0.44

 internetowa

-0.43

POSITIVE LOGITS

 createState

0.80

 المعيارى

0.80

 uParam

0.79

=$((

0.77

{{$

0.75

="{{$

0.74

Οι

0.73

(!__

0.72

 MonoBehaviour

0.71

 AppComponent

0.69

Activations Density 0.039%

occurrences of the "@" symbol, indicating mentions or tags

No Comments

No Known Activations