INDEX

Explanations

technical or programming terms related to buffer overflow vulnerabilities

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

C source code, struct, or file names

np_acts-logits-general · gemini-2.0-flash

storage or stub definitions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

It

-0.52

sfw

-0.47

 come

-0.46

/"+

-0.46

:][

-0.45

 sinds

-0.45

?}",

-0.45

/")

-0.45

/'+

-0.44

folium

-0.43

POSITIVE LOGITS

__

0.92

 purpoſe

0.92

 pleaſure

0.88

 myſelf

0.87

 Monfieur

0.87

 houſe

0.85

 perſon

0.80

 ſeveral

0.80

0.79

 Majefty

0.79

Activations Density 0.739%

technical or programming terms related to buffer overflow vulnerabilities

C source code, struct, or file names

storage or stub definitions

No Comments

No Known Activations