INDEX

Explanations

terms related to specific conditions or classifications within various contexts

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

 already

-0.51

 have

-0.48

 find

-0.46

 make

-0.44

 need

-0.44

 netto

-0.44

get

-0.43

ähkö

-0.43

 give

-0.43

 keep

-0.43

POSITIVE LOGITS

ScopeManager

0.93

AddTagHelper

0.92

StoryboardSegue

0.90

 utafitiHapana

0.85

aarrggbb

0.84

ReusableCell

0.83

 للمعارف

0.82

 combineReducers

0.80

principalTable

0.80

 AssemblyCulture

0.80

Activations Density 0.531%

terms related to specific conditions or classifications within various contexts

No Comments

No Known Activations