INDEX

Explanations

words related to consequences or potential outcomes

oai_token-act-pair · gpt-3.5-turbo

discussions about potential consequences or effects of various subjects

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vez

-0.78

oned

-0.74

ced

-0.72

yards

-0.69

este

-0.69

cker

-0.68

zig

-0.68

ten

-0.66

cÃ©

-0.66

ved

-0.65

POSITIVE LOGITS

 implications

1.20

 ramifications

1.04

 fallout

0.91

 repercussions

0.88

 consequences

0.86

 Impl

0.85

 implication

0.83

 impacts

0.80

 impact

0.77

 ripple

0.76

Activations Density 0.013%

words related to consequences or potential outcomes

discussions about potential consequences or effects of various subjects

No Comments

No Known Activations