INDEX

Explanations

concepts related to extensive lists or databases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

riwal

-0.76

PhysRevLett

-0.72

ConstraintMaker

-0.69

bouts

-0.66

WriteTagHelper

-0.65

ManagedBean

-0.62

#+#

-0.61

HandlerContext

-0.61

SourceChecksum

-0.61

XtraReports

-0.60

POSITIVE LOGITS

 hundreds

0.95

 thousands

0.90

Thousands

0.85

 multitude

0.85

hundreds

0.83

thousands

0.82

 innumerable

0.80

 Hundreds

0.80

 Thousands

0.78

 countless

0.77

Activations Density 0.487%

concepts related to extensive lists or databases

No Comments

No Known Activations