INDEX

Explanations

complex terms related to mapping or categorization

oai_token-act-pair · gpt-3.5-turbo

terms related to effort and attention to detail

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 deviations

-0.80

 redund

-0.72

 concessions

-0.72

 adaptations

-0.72

 characterization

-0.70

 involve

-0.68

 reservations

-0.68

 exceptions

-0.68

 venues

-0.68

 embodiments

-0.67

POSITIVE LOGITS

Dutch

0.79

Supporters

0.74

Leaks

0.73

lesi

0.72

lee

0.72

atform

0.71

odox

0.69

anon

0.68

yssey

0.68

clinton

0.67

Activations Density 0.000%

complex terms related to mapping or categorization

terms related to effort and attention to detail

No Comments

No Known Activations