INDEX

Explanations

mentions of trees and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 ſeveral

-1.16

 Monfieur

-1.16

 myſelf

-1.15

 themſelves

-1.15

 pleaſure

-1.14

Eſ

-1.09

 greateſt

-1.06

 himſelf

-1.06

 Majefty

-1.06

✨:

-1.05

POSITIVE LOGITS

 trees

2.11

 tree

2.10

 Tree

2.00

 Trees

1.96

 TREE

1.91

Trees

1.75

Tree

1.73

tree

1.68

 TREES

1.60

TREE

1.60

Activations Density 0.047%

mentions of trees and related terms

No Comments

No Known Activations