INDEX

Explanations

anomalies or deviations

oai_token-act-pair · gpt-3.5-turbo

terms related to anomalies and abnormalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fare

-0.83

estern

-0.80

orney

-0.77

rol

-0.77

sol

-0.76

cery

-0.76

nut

-0.76

Aid

-0.74

ners

-0.74

heed

-0.73

POSITIVE LOGITS

 Detected

0.89

 specimens

0.85

 anomalies

0.79

 faults

0.73

 arte

0.71

 anomaly

0.71

 Scotia

0.70

 specimen

0.66

ographs

0.62

 fossils

0.61

Activations Density 0.027%

anomalies or deviations

terms related to anomalies and abnormalities

No Comments

No Known Activations