INDEX

Explanations

technical terms and codes related to URL manipulation and HTTP request handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

PropertyChanging

-0.55

 Bress

-0.48

entin

-0.47

 circ

-0.45

horabuena

-0.45

abetes

-0.44

uoco

-0.44

 nhân

-0.43

zése

-0.42

ECONDS

-0.41

POSITIVE LOGITS

 query

1.07

query

0.97

 Query

0.94

QueryString

0.90

Query

0.89

 queryParams

0.87

queryString

0.86

getQuery

0.85

QUERY

0.85

 queryString

0.83

Activations Density 0.207%

technical terms and codes related to URL manipulation and HTTP request handling

No Comments

No Known Activations