INDEX

Explanations

words related to intrusion or entry, especially forcefully or deeply

oai_token-act-pair · gpt-3.5-turbo

terms related to penetration or infiltration

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

rie

-0.78

rious

-0.73

tri

-0.70

 farewell

-0.69

bind

-0.66

 goodbye

-0.66

rug

-0.66

piece

-0.64

rieve

-0.64

killer

-0.63

POSITIVE LOGITS

 penetrated

1.11

 penetrate

1.08

 penetration

1.02

 penet

0.99

 infiltrated

0.91

 INTO

0.89

 deeper

0.86

 penetrating

0.83

 into

0.83

 infiltrate

0.83

Activations Density 0.032%

words related to intrusion or entry, especially forcefully or deeply

terms related to penetration or infiltration

No Comments

No Known Activations