INDEX

Explanations

references to extracts and their effects in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Bourgoin

-0.88

ंदीखरीदारी

-0.87

createClass

-0.81

Rhestr

-0.81

 ModelRenderer

-0.80

 cherchés

-0.80

 pleaſure

-0.80

 bezeichneter

-0.80

tagHelperRunner

-0.79

queryInterface

-0.78

POSITIVE LOGITS

 quest

0.73

gs

0.69

 Quest

0.67

 spectra

0.66

 spectrum

0.64

quest

0.63

 extract

0.61

 enforcing

0.59

Extract

0.57

 enforcement

0.56

Activations Density 0.073%

references to extracts and their effects in scientific contexts

No Comments

No Known Activations