INDEX

Explanations

statements confirming the correctness of opinions or arguments

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

AKER

-0.59

ópolis

-0.54

MENAFN

-0.52

PARATION

-0.52

ixe

-0.51

intend

-0.50

jem

-0.50

lossal

-0.49

 Standard

-0.49

 Command

-0.49

POSITIVE LOGITS

 صوتيه

0.90

 disagrees

0.69

 Infórmanos

0.67

 wrong

0.67

niosek

0.66

Efq

0.64

 HasFactory

0.63

reszcie

0.63

 فريبيس

0.62

 auffi

0.61

Activations Density 0.131%

statements confirming the correctness of opinions or arguments

No Comments

No Known Activations