INDEX

Explanations

code comments or documentation strings

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

lapsingToolbar

-0.87

raphe

-0.71

 Helms

-0.70

 Azam

-0.69

 Helga

-0.66

 initComponents

-0.66

AnchorStyles

-0.66

 المعيارى

-0.66

Jha

-0.64

 Heber

-0.63

POSITIVE LOGITS

[]:

0.81

 doInBackground

0.76

python

0.71

"""

0.70

VolleyError

0.68

 predicts

0.65

 prediction

0.64

 Predictions

0.64

 Prediction

0.63

Python

0.62

Activations Density 0.051%

code comments or documentation strings

No Comments

No Known Activations