INDEX

Explanations

negative descriptors related to conditions or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AddTagHelper

-0.82

SequentialGroup

-0.75

IntoConstraints

-0.74

⟬

-0.73

rungsseite

-0.70

 transfieras

-0.67

Cyfarwyddwr

-0.66

 GetEnumerator

-0.65

iibo

-0.65

OGND

-0.65

POSITIVE LOGITS

Bad

0.85

bad

0.84

Bad

0.80

Worse

0.77

Worst

0.77

 worse

0.76

 worst

0.76

BAD

0.73

 horrible

0.72

worst

0.71

Activations Density 0.315%

negative descriptors related to conditions or consequences

No Comments

No Known Activations