INDEX

Explanations

notations or variables related to programming or mathematical concepts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 themſelves

-1.18

 ſeveral

-1.13

 myſelf

-1.11

 ſever

-1.06

 himſelf

-1.05

 Monfieur

-1.04

 raiſ

-1.01

ſelf

-0.98

 ſind

-0.98

 doubtnut

-0.97

POSITIVE LOGITS

1.88

1.82

1.53

1.38

 getC

1.24

1.15

setC

1.14

1.11

1.04

1.01

Activations Density 0.230%

notations or variables related to programming or mathematical concepts

No Comments

No Known Activations