INDEX

Explanations

commands and functions related to tensor manipulation in TensorFlow

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 للاسماء

-0.96

WebVitals

-0.90

Efq

-0.90

rshire

-0.83

 Monfieur

-0.82

+#+

-0.82

 pngtree

-0.81

extAlignment

-0.79

 Reſ

-0.77

 Theſe

-0.77

POSITIVE LOGITS

tf

1.90

tf

1.58

TF

1.16

TF

1.11

Tf

0.94

 tensorflow

0.81

Tf

0.80

 TensorFlow

0.66

tensorflow

0.65

 distanciation

0.48

Activations Density 0.119%

commands and functions related to tensor manipulation in TensorFlow

No Comments

No Known Activations