INDEX

Explanations

references to specific dates and events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" within the text

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

 ster

-0.68

Reviewer

-0.65

 WITHOUT

-0.61

 perv

-0.61

 unnecess

-0.61

 wield

-0.60

irs

-0.60

 penet

-0.60

enser

-0.59

 likened

-0.58

POSITIVE LOGITS

 February

1.83

 January

1.79

1.77

 December

1.77

 April

1.77

 September

1.76

 October

1.75

 November

1.73

 August

1.72

Activations Density 0.301%

references to specific dates and events

occurrences of the word "in" within the text

No Comments

No Known Activations