INDEX

Explanations

terms related to proximity or adjacency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

istoitu

-0.61

pustakaan

-0.50

InputTagHelper

-0.47

 تضيفلها

-0.46

complexType

-0.46

SuppressLint

-0.45

MigrationBuilder

-0.44

Ist

-0.44

rtype

-0.43

 hashCode

-0.41

POSITIVE LOGITS

Nearby

0.81

 Nachbarn

0.81

 Nearby

0.79

 nearby

0.75

 Nachbar

0.74

nearby

0.73

neighbor

0.72

Neighbor

0.72

 Neigh

0.72

 neighboring

0.72

Activations Density 0.270%

terms related to proximity or adjacency

No Comments

No Known Activations