INDEX

Explanations

references to iterative processes or structures in programming

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

 grunn

-0.65

发表于

-0.64

لاثة

-0.62

mä

-0.61

Soo

-0.61

Pl

-0.60

 Sache

-0.59

fontawesome

-0.59

 superiori

-0.58

haupt

-0.57

POSITIVE LOGITS

 iter

1.77

 Iter

1.67

iter

1.55

 iterator

1.54

Iter

1.52

Iterator

1.49

 iterations

1.44

 Iterator

1.43

 Iteration

1.35

 iteration

1.34

Activations Density 0.080%

references to iterative processes or structures in programming

No Comments

No Known Activations