INDEX

Explanations

identifiers or specific terms related to events and actions in programming or legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 Audiodateien

-0.67

 Infórmanos

-0.66

principalTable

-0.65

AddTagHelper

-0.63

 للمعارف

-0.63

 Italijanski

-0.62

település

-0.62

PMailer

-0.61

Биография

-0.61

POSITIVE LOGITS

evt

1.17

evt

1.16

Evt

0.69

 eyewitness

0.44

vw

0.43

 eyew

0.42

EVT

0.41

*)

0.39

 pulse

0.38

 Pulse

0.36

Activations Density 0.001%

identifiers or specific terms related to events and actions in programming or legal contexts

No Comments

No Known Activations