INDEX

Explanations

terms related to prediction and predictability

oai_token-act-pair · gpt-3.5-turbo

terms related to prediction and predictive analysis

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

Negative Logits

dx

-0.76

 Antiqu

-0.74

unal

-0.70

untu

-0.68

HOME

-0.67

cca

-0.67

ento

-0.65

undy

-0.64

 Wine

-0.63

Ou

-0.62

POSITIVE LOGITS

 Predict

1.05

 predict

0.99

itability

0.96

ively

0.93

ably

0.91

redict

0.89

ability

0.87

 unpredict

0.87

 predictive

0.85

 probabilities

0.83

Activations Density 0.019%

terms related to prediction and predictability

terms related to prediction and predictive analysis

No Known Activations