INDEX

Explanations

terminology related to frameworks and structured systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

RenderAtEndOf

-0.83

MigrationBuilder

-0.79

 CreateTagHelper

-0.64

íslu

-0.63

zczegól

-0.62

DebuggerStep

-0.60

raisemb

-0.59

 uParam

-0.58

 pleaf

-0.57

ButterKnife

-0.57

POSITIVE LOGITS

ExtendWith

0.64

rupa

0.60

Portale

0.60

\}\\

0.60

 framework

0.59

Demografia

0.59

schema

0.59

WindowConstants

0.59

Билгалдахарш

0.59

 special

0.58

Activations Density 0.104%

terminology related to frameworks and structured systems

No Comments

No Known Activations