INDEX

Explanations

discussions and references to various theories and models in academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

IBarButtonItem

-0.63

setViewportView

-0.63

ellites

-0.55

 abgerufen

-0.54

ufnahme

-0.53

createCell

-0.52

licia

-0.51

ihnachten

-0.51

ihnachts

-0.50

randomUUID

-0.50

POSITIVE LOGITS

InjectAttribute

0.74

 autorytatywna

0.72

 underpin

0.71

 ProtoMessage

0.69

IUrlHelper

0.66

InstrumentedTest

0.64

 concepts

0.61

پرد

0.61

 Principe

0.60

ResumeLayout

0.60

Activations Density 0.165%

discussions and references to various theories and models in academic contexts

No Comments

No Known Activations