INDEX

Explanations

sections containing technical specifications or terms related to medical or scientific content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ViewFeatures

-0.84

:],

-0.69

-0.60

antd

-0.59

stdc

-0.58

 صوتيه

-0.55

-0.54

лючение

-0.53

ppur

-0.53

 MonoBehaviour

-0.53

POSITIVE LOGITS

 raiſ

0.96

 purpoſe

0.92

 ſaid

0.91

 Inſ

0.90

 pleaſure

0.89

 uſed

0.89

 Theſe

0.88

 Jefus

0.88

 Reſ

0.85

 himſelf

0.85

Activations Density 0.937%

sections containing technical specifications or terms related to medical or scientific content

No Comments

No Known Activations