INDEX

Explanations

references to structural components and identifiers within a programming or organizational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

tal

-0.75

ton

-0.73

ty

-0.71

co

-0.68

式

-0.67

the

-0.66

type

-0.66

tra

-0.66

POSITIVE LOGITS

ſelves

0.99

hips

0.97

Jaunes

0.96

citenamefont

0.92

helves

0.91

]")]

0.91

 Taktlose

0.91

 doubtnut

0.87

 '\\;'

0.87

 indisponible

0.84

Activations Density 3.939%

references to structural components and identifiers within a programming or organizational context

No Comments

No Known Activations