INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Neo

-0.65

-0.61

shared

-0.60

 POST

-0.60

CAM

-0.57

ombo

-0.57

SY

-0.56

SAM

-0.56

SHA

-0.56

zees

-0.56

POSITIVE LOGITS

PIN

0.75

effic

0.72

cest

0.69

inventoryQuantity

0.69

externalActionCode

0.68

ĸļ

0.67

 analogy

0.67

Phill

0.66

Educ

0.65

 impression

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.