INDEX

Explanations

occurrences of solutions or methods that address challenges or obstacles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-1.07

NUMX

-0.98

 itſelf

-0.95

 ſtate

-0.94

 pleaſure

-0.91

 raiſ

-0.89

 themſelves

-0.89

 purpoſe

-0.88

 ſmall

-0.87

 faſt

-0.87

POSITIVE LOGITS

em

0.82

Em

0.75

emb

0.74

em

0.70

Em

0.68

Emb

0.67

EM

0.63

Emb

0.61

 matter

0.60

 ими

0.53

Activations Density 0.121%

occurrences of solutions or methods that address challenges or obstacles

No Comments

No Known Activations