INDEX

Explanations

references to combinations of elements or entities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

RectangleBorder

-0.81

JSONException

-0.63

 informée

-0.63

UserScript

-0.62

 Numerade

-0.60

Puck

-0.58

webElementXpaths

-0.57

 Normdatei

-0.56

 برانيه

-0.56

ControllerAdvice

-0.54

POSITIVE LOGITS

 combinations

0.89

 houſe

0.81

 their

0.81

combinations

0.81

Their

0.77

 Their

0.76

 combination

0.76

 themſelves

0.75

combo

0.73

 combo

0.73

Activations Density 0.133%

references to combinations of elements or entities in various contexts

No Comments

No Known Activations