INDEX

Explanations

terms related to mathematical expressions and computations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

orteur

-0.59

lioz

-0.45

obar

-0.45

{#

-0.44

zea

-0.44

 firma

-0.43

rive

-0.43

矶

-0.43

PositiveButton

-0.42

ರು

-0.41

POSITIVE LOGITS

 recurrence

0.91

 recursion

0.86

 Recur

0.84

Дереккөздер

0.74

 Fibonacci

0.72

Recur

0.71

tonode

0.69

Fibonacci

0.69

 recursive

0.68

 recur

0.68

Activations Density 1.487%

terms related to mathematical expressions and computations

No Comments

No Known Activations