INDEX

Explanations

sentences that convey significant information or conclusions, particularly in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Aholisi

-0.52

bkz

-0.51

puh

-0.45

pett

-0.45

Ibid

-0.45

 himself

-0.44

 snabb

-0.44

 kuni

-0.44

 Ofer

-0.43

 blanches

-0.43

POSITIVE LOGITS

 doInBackground

0.95

WriteTagHelper

0.93

 typelib

0.84

 snippetHide

0.73

KURZBESCHREIBUNG

0.70

 AssemblyCulture

0.70

 CreateTagHelper

0.70

клопе

0.69

 ویکی‌پدی

0.66

BASEPATH

0.66

Activations Density 0.241%

sentences that convey significant information or conclusions, particularly in scientific contexts

No Comments

No Known Activations