INDEX

Explanations

references to product features and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 astore

-0.61

 оригіналу

-0.61

InjectAttribute

-0.61

errHandler

-0.60

AddTagHelper

-0.57

DMETHOD

-0.56

хіво

-0.55

AccessorTable

-0.54

 насељу

-0.54

abestanden

-0.54

POSITIVE LOGITS

MigrationBuilder

0.74

0.71

️

0.70

ográficas

0.70

︎

0.69

್

0.67

്

0.67

herin

0.64

racene

0.62

्

0.61

Activations Density 0.295%

references to product features and specifications

No Comments

No Known Activations