INDEX

Explanations

occurrences of the word "trace" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

pagni

-0.87

feitura

-0.79

getInteger

-0.76

kowski

-0.75

tetten

-0.74

kman

-0.71

地说道

-0.71

lasma

-0.70

 McGovern

-0.69

bukkit

-0.69

POSITIVE LOGITS

 Trace

1.47

 trace

1.37

 Traces

1.33

Trace

1.29

 traces

1.28

trace

1.26

 TRACE

1.24

traces

1.23

 traced

1.22

Traces

1.16

Activations Density 0.083%

occurrences of the word "trace" in various contexts

No Comments

No Known Activations