INDEX

Explanations

verbs associated with actions or activities

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

fes

-0.74

defineProperty

-0.64

coli

-0.60

het

-0.55

CodeDom

-0.54

allus

-0.54

ses

-0.54

مرت

-0.53

 lazos

-0.52

antia

-0.52

POSITIVE LOGITS

 CreateTagHelper

1.00

uxxxx

0.87

MLLoader

0.76

SEGUIR

0.74

 незавершена

0.74

FieldBuilder

0.71

migrationBuilder

0.69

elemField

0.68

zeba

0.67

barrow

0.66

Activations Density 0.071%

verbs associated with actions or activities

No Comments

No Known Activations