INDEX

Explanations

measurements or numerical data, such as distances, percentages, or ratings

oai_token-act-pair · gpt-3.5-turbo

numerical values or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

raltar

-0.89

isition

-0.74

umbn

-0.74

rament

-0.72

ylum

-0.70

akespe

-0.69

resso

-0.68

lication

-0.67

omnia

-0.66

lder

-0.66

POSITIVE LOGITS

 lakh

0.88

ERA

0.83

 WRITE

0.82

 crore

0.80

 trillion

0.76

 Ranked

0.76

GHz

0.75

Â±

0.72

Bog

0.72

 mills

0.72

Activations Density 0.059%

measurements or numerical data, such as distances, percentages, or ratings

numerical values or statistics

No Comments

No Known Activations