INDEX

Explanations

references to performing actions or tasks, especially in a functional or service-oriented context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 estimés

-0.61

Incoming

-0.56

참고

-0.56

help

-0.56

RenderAtEndOf

-0.55

 yeezy

-0.52

Stability

-0.52

Zat

-0.51

 dass

-0.50

 Laurens

-0.50

POSITIVE LOGITS

 perform

1.12

 Perform

1.10

 performed

1.05

 PERFORM

1.04

performed

1.03

 performs

1.01

Perform

0.97

 Performs

0.95

performs

0.92

 Performing

0.90

Activations Density 0.119%

references to performing actions or tasks, especially in a functional or service-oriented context

No Comments

No Known Activations