INDEX

Explanations

sponsorship-related terms

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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.82

otom

-0.77

aults

-0.74

 pend

-0.73

asure

-0.71

izabeth

-0.69

pH

-0.69

cester

-0.68

 msec

-0.66

olit

-0.66

POSITIVE LOGITS

hips

0.99

orship

0.97

 sponsor

0.94

 sponsorship

0.93

 sponsoring

0.92

 sponsored

0.90

 sponsors

0.88

Spons

0.82

paren

0.79

sponsored

0.75

Activations Density 0.026%

sponsorship-related terms

terms related to sponsorship

No Comments

No Known Activations