INDEX

Explanations

references to legal and law enforcement activities

oai_token-act-pair · gpt-3.5-turbo

references to legal cases and court decisions

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

 realised

-0.90

 realise

-0.85

 Whilst

-0.84

 fulfil

-0.84

 endeavour

-0.83

 whilst

-0.81

 behaviours

-0.74

 learnt

-0.73

 behaviour

-0.73

 organise

-0.72

POSITIVE LOGITS

 statewide

0.90

 subpoen

0.89

 federally

0.86

 federal

0.82

 Wisconsin

0.81

 Pennsylvania

0.78

 bipartisan

0.76

 FOIA

0.76

 congressional

0.75

 Maryland

0.75

Activations Density 2.673%

references to legal and law enforcement activities

references to legal cases and court decisions

No Comments

No Known Activations