INDEX

Explanations

the word "that" in various contexts and frequencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

DockStyle

-0.56

konomi

-0.48

-0.47

BorderSize

-0.47

 näytte

-0.47

viembre

-0.46

multicolumn

-0.46

 Hopf

-0.46

</thead>

-0.45

 bienven

-0.45

POSITIVE LOGITS

########.

0.76

rungsseite

0.68

مصادر

0.67

 Reverso

0.64

 للمعارف

0.62

:+:

0.61

+#+

0.60

"]];

0.59

GOTREF

0.58

 विश्वसनीयता

0.58

Activations Density 0.214%

the word "that" in various contexts and frequencies

No Comments

No Known Activations