INDEX

Explanations

phrases that indicate a sequence of arguments or justifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

ніципалі

-0.46

dư

-0.45

TestingModule

-0.44

 ktorí

-0.43

จัง

-0.40

itinéraire

-0.39

expandindo

-0.38

asanjo

-0.38

razine

-0.37

+:+

-0.36

POSITIVE LOGITS

AxisAlignment

0.76

AccessorTable

0.75

 ErrIntOverflow

0.74

WriteTagHelper

0.69

 (!__

0.66

HomeAsUpEnabled

0.66

BagConstraints

0.66

BufferException

0.65

ثيق

0.63

//$

0.63

Activations Density 0.317%

phrases that indicate a sequence of arguments or justifications

No Comments

No Known Activations