INDEX

Explanations

mentions of sponsors or sponsored content

oai_token-act-pair · gpt-3.5-turbo

terms related to sponsorship

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

selves

-0.77

 pend

-0.75

otom

-0.72

izabeth

-0.71

itri

-0.69

cale

-0.68

 msec

-0.67

asure

-0.67

olit

-0.67

juries

-0.66

POSITIVE LOGITS

hips

1.00

 sponsor

0.95

orship

0.94

 sponsorship

0.91

 sponsors

0.90

 sponsoring

0.89

 sponsored

0.87

Spons

0.85

sponsored

0.76

 Spons

0.74

Activations Density 0.024%

mentions of sponsors or sponsored content

terms related to sponsorship

No Comments

No Known Activations