INDEX

Explanations

terms related to forensic evidence and archaeological findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

lebo

-0.49

axel

-0.49

hips

-0.48

PhysRevLett

-0.47

PhysRevD

-0.46

URLException

-0.46

تماد

-0.45

اں

-0.45

PAS

-0.45

ziell

-0.44

POSITIVE LOGITS

RenderAtEndOf

0.72

 traces

0.68

 Remains

0.68

 ruines

0.67

traces

0.66

 resourceCulture

0.66

 remnants

0.64

 bekas

0.63

 ruins

0.63

Traces

0.63

Activations Density 0.432%

terms related to forensic evidence and archaeological findings

No Comments

No Known Activations