INDEX

Explanations

negative phrases or constructs indicating dissatisfaction or inadequacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

+#+#

-0.59

OGND

-0.57

IndentedString

-0.56

іга

-0.55

первых

-0.55

 Nauk

-0.53

 سكانية

-0.53

ftagPool

-0.52

conditionally

-0.50

 Drapeau

-0.48

POSITIVE LOGITS

 adequately

0.81

 adequate

0.80

 properly

0.75

 satisfactory

0.73

 sufficiently

0.67

 quite

0.66

 Quite

0.64

 otomatig

0.63

 sufficient

0.63

 timely

0.63

Activations Density 0.539%

negative phrases or constructs indicating dissatisfaction or inadequacy

No Comments

No Known Activations