INDEX

Explanations

connections and relationships between concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

DebuggerStep

-0.39

 options

-0.36

SourceChecksum

-0.36

twimg

-0.35

 ditemp

-0.35

 opport

-0.35

 counted

-0.35

 smě

-0.35

:✨

-0.34

gere

-0.34

POSITIVE LOGITS

 linked

1.14

Linked

1.06

linked

1.05

 Linked

1.04

 tied

1.02

 connected

1.00

 Tied

0.95

 Connected

0.91

connected

0.91

 linkage

0.88

Activations Density 0.658%

connections and relationships between concepts or entities

No Comments

No Known Activations