INDEX

Explanations

descriptions or discussions viewed through a critical or evaluative lens

oai_token-act-pair · gpt-3.5-turbo

perspectives related to viewing situations through different lenses or frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 ensued

-0.77

 caches

-0.72

 persisted

-0.69

 Wonders

-0.66

 Registry

-0.65

 renown

-0.64

itol

-0.64

 avail

-0.62

laus

-0.61

 registrations

-0.60

POSITIVE LOGITS

 perspective

1.10

 context

1.09

 terms

0.99

 totality

0.95

 prism

0.90

 broader

0.90

 differently

0.88

 retrospect

0.82

 hindsight

0.81

 lens

0.80

Activations Density 0.250%

descriptions or discussions viewed through a critical or evaluative lens

perspectives related to viewing situations through different lenses or frameworks

No Comments

No Known Activations