INDEX

Explanations

descriptions of conditions or qualities related to objects, people, or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

timewa

-0.67

可惜

-0.51

 smoother

-0.49

InputTagHelper

-0.48

omeness

-0.47

 recommandée

-0.46

 Ruhe

-0.46

lrrrr

-0.45

stances

-0.45

HttpEntity

-0.45

POSITIVE LOGITS

 poor

0.96

poor

0.94

Poor

0.88

 cheap

0.83

 Poor

0.82

 POOR

0.81

 poorest

0.79

Cheap

0.78

 rudimentary

0.78

 cheaply

0.77

Activations Density 0.551%

descriptions of conditions or qualities related to objects, people, or situations

No Comments

No Known Activations