INDEX

Explanations

negative sentiment or expressions indicating decline or loss

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 zelve

-0.61

 שוליים

-0.61

 Infór

-0.59

 desmotivaciones

-0.58

 Gerechtigkeit

-0.58

printStackTrace

-0.56

 InputDecoration

-0.56

 GoogleFonts

-0.54

 éstos

-0.54

 pérd

-0.53

POSITIVE LOGITS

0.97

–

0.68

0.67

%-

0.64

()-

0.62

]-

0.61

-<

0.60

‐

0.60

)-

0.60

‑

0.59

Activations Density 0.032%

negative sentiment or expressions indicating decline or loss

No Comments

No Known Activations