INDEX

Explanations

estimates or estimations related to various subjects

oai_token-act-pair · gpt-3.5-turbo

references to statistical estimates or numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

woods

-0.88

matter

-0.83

feeding

-0.80

Interstitial

-0.76

wood

-0.75

ierre

-0.72

oard

-0.71

artney

-0.71

marine

-0.71

interrupted

-0.71

POSITIVE LOGITS

 estimates

1.02

 estimate

1.01

imate

1.00

imates

0.93

 estimating

0.88

 Estimates

0.81

 valuation

0.77

 estimated

0.77

 estimation

0.75

 estim

0.74

Activations Density 0.032%

estimates or estimations related to various subjects

references to statistical estimates or numerical data

No Comments

No Known Activations