INDEX

Explanations

responses indicating user activity or status updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 BoxDecoration

-0.98

-0.91

 صوتيه

-0.84

 iſt

-0.82

出版年

-0.81

RTLR

-0.80

 كومونز

-0.79

ագրություններ

-0.77

 ſind

-0.77

 sandero

-0.76

POSITIVE LOGITS

↵↵

0.89

<eos>

0.81

The

0.77

The

0.69

0.68

No

0.65

↵

0.64

0.62

0.61

Activations Density 0.232%

responses indicating user activity or status updates

No Comments

No Known Activations