INDEX

Explanations

numerical values related to specific content or information like article IDs or dates

oai_token-act-pair · gpt-3.5-turbo

numeric identifiers or codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ierrez

-0.82

oulos

-0.77

brace

-0.76

aughs

-0.71

anooga

-0.70

chio

-0.65

 DRAG

-0.65

 nomine

-0.64

 Beir

-0.63

 Combine

-0.63

POSITIVE LOGITS

0.98

0.97

0.96

0.95

Activations Density 0.099%

numerical values related to specific content or information like article IDs or dates

numeric identifiers or codes

No Comments

No Known Activations