INDEX

Explanations

terms related to long-term duration or foresight

oai_token-act-pair · gpt-3.5-turbo

references to long-term concepts or considerations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cosponsors

-0.99

HOU

-0.87

 DRAG

-0.81

chu

-0.81

chy

-0.78

hou

-0.77

rote

-0.77

IDES

-0.76

 Mansion

-0.76

©¶æ¥µ

-0.74

POSITIVE LOGITS

 viability

0.98

 stability

0.85

 survival

0.81

 sustainability

0.80

 unemployed

0.79

 impact

0.79

 usefulness

0.78

 memory

0.77

 outcomes

0.77

 outcome

0.75

Activations Density 0.022%

terms related to long-term duration or foresight

references to long-term concepts or considerations

No Comments

No Known Activations