INDEX

Explanations

words related to the concept of chipping or chipped

oai_token-act-pair · gpt-3.5-turbo

words related to gradual consumption or degradation

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

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

 Defin

-0.74

 guiName

-0.73

 damned

-0.72

taboola

-0.71

geist

-0.70

ADRA

-0.67

 Palest

-0.66

 Surviv

-0.65

Zed

-0.63

da

-0.62

POSITIVE LOGITS

etsk

0.91

psey

0.88

ilateral

0.85

otent

0.84

rocal

0.82

arent

0.81

ips

0.78

insula

0.77

ule

0.76

avascript

0.75

Activations Density 0.011%

words related to the concept of chipping or chipped

words related to gradual consumption or degradation

No Comments

No Known Activations