INDEX

Explanations

fluctuations or changes in quantities or values

oai_token-act-pair · gpt-3.5-turbo

terms related to increases or rises in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tta

-0.89

 Founding

-0.75

sol

-0.71

mates

-0.70

thing

-0.67

mun

-0.66

prison

-0.65

pora

-0.64

been

-0.64

mir

-0.64

POSITIVE LOGITS

 sharply

0.97

 steadily

0.95

 exponentially

0.93

 dramatically

0.91

 markedly

0.89

 tremend

0.88

 considerably

0.84

 enormously

0.84

 explos

0.82

 accordingly

0.82

Activations Density 0.119%

fluctuations or changes in quantities or values

terms related to increases or rises in various contexts

No Comments

No Known Activations