INDEX

Explanations

instructions or prompts to continue reading or to access more information

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

CWE

-0.75

 تانيه

-0.71

::~

-0.69

 propOrder

-0.64

 normaux

-0.63

omores

-0.62

最快更新

-0.61

pantalones

-0.61

 ordinario

-0.60

 dezelve

-0.60

POSITIVE LOGITS

<eos>

0.63

 дописавши

0.55



0.54

 link

0.54

tri

0.53

 >=",

0.52

 getchar

0.51

tric

0.49

DebuggerStep

0.49

 برانيه

0.49

Activations Density 0.254%

instructions or prompts to continue reading or to access more information

No Comments

No Known Activations