INDEX

Explanations

references to laws, legal terms, and judicial processes

oai_token-act-pair · gpt-3.5-turbo

references to significant events or actions within a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Secondly

-0.83

nesday

-0.80

////////////////

-0.77

ruary

-0.74

sequently

-0.73

çīĪ

-0.72

anwhile

-0.70

£ı

-0.70

Ô

-0.70

REDACTED

-0.68

POSITIVE LOGITS

 sentencing

0.57

 sexually

0.55

 criminal

0.55

 offenses

0.54

 felony

0.53

 hurt

0.52

 grip

0.51

 sting

0.50

 damaging

0.49

 assault

0.49

Activations Density 1.116%

references to laws, legal terms, and judicial processes

references to significant events or actions within a narrative context

No Comments

No Known Activations