INDEX

Explanations

terms related to the concept of "existing" or "current"

oai_token-act-pair · gpt-3.5-turbo

references to pre-established systems or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ertodd

-0.88

alion

-0.77

romeda

-0.75

ÃŃa

-0.73

umbo

-0.72

owitz

-0.72

ousse

-0.71

ique

-0.70

olog

-0.70

phasis

-0.70

POSITIVE LOGITS

existing

0.91

 exting

0.84

 existing

0.84

IRE

0.80

entials

0.76

 liabilities

0.75

ãĤ´

0.75

foundland

0.72

 selves

0.69

 arrangements

0.69

Activations Density 0.014%

terms related to the concept of "existing" or "current"

references to pre-established systems or conditions

No Comments

No Known Activations