INDEX

Explanations

references to figures in a document

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 ་་

-0.71

 derer

-0.71

Дереккөздер

-0.69

[...]

-0.69

parsedMessage

-0.69

Okay

-0.68

 rime

-0.68

 fume

-0.68

#>

-0.68

venu

-0.67

POSITIVE LOGITS

Fig

3.35

Fig

3.18

 Figs

2.39

Figs

2.22

fig

2.04

fig

1.83

FIG

1.69

 figs

1.52

FIG

1.46

Aug

1.32

Activations Density 0.162%

references to figures in a document

No Comments

No Known Activations