INDEX

Explanations

keywords and phrases associated with API requests and data structures

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

Tokens before capitalized words like "API", "Request", or "Select"

np_acts-logits-general · gemini-2.0-flash

API Request

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

GeoNames

-0.60

HasBeenSet

-0.55

featureID

-0.54

MigrationBuilder

-0.53

TextHelper

-0.53

paramref

-0.53

RepeatedField

-0.53

openzeppelin

-0.52

TagMode

-0.50

<",

-0.50

POSITIVE LOGITS

Efq

0.68

 transfieras

0.66

 themſelves

0.64

yaitu

0.63

 InputDecoration

0.63

mereka

0.60

neſs

0.60

reportWebVitals

0.59

 moro

0.59

 ſeveral

0.58

Activations Density 0.220%

keywords and phrases associated with API requests and data structures

Tokens before capitalized words like "API", "Request", or "Select"

API Request

No Comments

No Known Activations