INDEX

Explanations

references to data transmission, specifically related to bandwidth and latency

oai_token-act-pair · gpt-3.5-turbo

terms related to network performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

neys

-0.76

 Kubrick

-0.74

bara

-0.74

inse

-0.71

ocrine

-0.70

inez

-0.68

 stern

-0.67

ku

-0.67

oan

-0.66

 Martinez

-0.64

POSITIVE LOGITS

 bandwidth

1.13

width

0.89

 throughput

0.85

 utilization

0.85

 spectrum

0.82

ibilities

0.80

 speeds

0.80

 acceleration

0.80

iencies

0.80

leneck

0.78

Activations Density 0.011%

references to data transmission, specifically related to bandwidth and latency

terms related to network performance metrics

No Comments

No Known Activations