INDEX

Explanations

references to the concept of improvement and aspects of glory

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-1.99

 itſelf

-1.98

Efq

-1.97

 Jefus

-1.84

 raiſ

-1.80

 themſelves

-1.80

 Majefty

-1.79

ſelves

-1.78

 poffible

-1.76

 ſtate

-1.75

POSITIVE LOGITS

0.95

0.93

↵↵

0.89

0.88

0.85

<eos>

0.84

In

0.83

to

0.82

Activations Density 0.217%

references to the concept of improvement and aspects of glory

No Comments

No Known Activations