INDEX

Explanations

technical terms and concepts in scientific contexts

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 propOrder

-0.46

tagext

-0.41

 bağı

-0.33

 interesar

-0.32

 berkata

-0.31

pura

-0.31

 distracting

-0.31

Jegyzetek

-0.30

'],

-0.30

 fortæller

-0.30

POSITIVE LOGITS

AsUp

0.68

AutoScaleMode

0.57

AndEndTag

0.55

DockStyle

0.54

SDF

0.53

verifyException

0.53

irited

0.53

Hymen

0.52

ſta

0.52

 BoxFit

0.51

Activations Density 0.278%

technical terms and concepts in scientific contexts

No Comments

No Known Activations