INDEX

Explanations

mentions of specific individuals in leadership positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

erved

-0.48

Shared

-0.48

CWE

-0.48

Par

-0.47

 logo

-0.47

dolo

-0.45

ilan

-0.45

abord

-0.45

 Army

-0.45

lores

-0.44

POSITIVE LOGITS

 personalmente

0.90

 personally

0.88

 persönlich

0.85

GenerationType

0.79

 himſelf

0.77

 himself

0.76

UnifiedTopology

0.70

principalTable

0.70

RTDA

0.69

CppMethod

0.68

Activations Density 0.378%

mentions of specific individuals in leadership positions

No Comments

No Known Activations