INDEX

Explanations

references to specific individuals or people

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "person" and its variations to identify individuals mentioned in the text

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

 Parables

-0.92

tnc

-0.81

IPM

-0.74

 Supplement

-0.70

âĺħâĺħ

-0.69

osterone

-0.65

Decre

-0.64

DOS

-0.63

 habitat

-0.63

 Reef

-0.62

POSITIVE LOGITS

uscript

0.90

afort

0.83

who

0.83

behind

0.83

 implicated

0.82

 smugglers

0.82

 whom

0.78

 testifying

0.76

 authorised

0.75

 involved

0.74

Activations Density 0.140%

references to specific individuals or people

occurrences of the word "person" and its variations to identify individuals mentioned in the text

No Comments

No Known Activations