INDEX

Explanations

patterns in function or method calls in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

"):

-0.59

'):

-0.59

'));

-0.58

]]

-0.58

"));

-0.57

TagMode

-0.57

']);

-0.56

()));

-0.55

]:

-0.55

 Inoc

-0.54

POSITIVE LOGITS

_;

0.67

_(

0.64

_.

0.62

_,

0.61

_-

0.58

_->

0.57

_[

0.56

_/

0.56

_{[

0.55

₉

0.54

Activations Density 0.029%

patterns in function or method calls in code

No Comments

No Known Activations