INDEX

Explanations

references to "beads" and their attributes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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



-1.06

 Oakes

-1.04

TCG

-0.99

-0.98

 שוליים

-0.98

 Claremont

-0.94

IsContent

-0.92

IDL

-0.92

ropractic

-0.91

akterysty

-0.91

POSITIVE LOGITS

 bead

0.69

 Bead

0.67

 depri

0.66

 sacco

0.66

an

0.65

Tom

0.62

Kus

0.62

 Minas

0.61

QueryParams

0.61

vang

0.60

Activations Density 2.347%

references to "beads" and their attributes in various contexts

No Comments

No Known Activations