INDEX

Explanations

phrases that indicate personal endorsement or recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

TagMode

-1.35

 AssemblyCulture

-1.11

AddTagHelper

-1.06

 Мексичка

-1.06

MLLoader

-0.96

ErrUnexpectedEOF

-0.93

mybatisplus

-0.91

ContentAsync

-0.91

 crdi

-0.90

ftagPool

-0.89

POSITIVE LOGITS

Dev

0.46

kez

0.43

 spoko

0.42

 stedet

0.41

 Facility

0.40

mele

0.40

Dev

0.39

ج

0.38

Service

0.38

Activations Density 0.027%

phrases that indicate personal endorsement or recommendations

No Comments

No Known Activations