INDEX

Explanations

repeated sequences of characters, likely focusing on specific patterns or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

webElement

-1.23

SourceChecksum

-1.17

 propOrder

-1.15

 OFDb

-1.06

principalTable

-1.05

expandindo

-1.02

ArrowToggle

-1.00

OGND

-1.00

mybatisplus

-0.97

MessageTagHelper

-0.96

POSITIVE LOGITS

0.77

Mc

0.53

يرا

0.52

CJK

0.52

\\[

0.51

keits

0.50

mauer

0.50

สือ

0.50

 berp

0.48

delo

0.48

Activations Density 0.087%

repeated sequences of characters, likely focusing on specific patterns or identifiers

No Comments

No Known Activations