INDEX

Explanations

mentions of personal experiences or encounters

oai_token-act-pair · gpt-3.5-turbo

mentions of personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

upper

-0.71

cial

-0.66

cut

-0.62

trump

-0.62

ump

-0.62

 decimal

-0.61

mask

-0.60

putable

-0.60

upp

-0.60

Correction

-0.59

POSITIVE LOGITS

 experiences

3.81

 experience

2.49

 experien

2.02

 Experience

1.86

 encounters

1.82

 exper

1.76

 Exper

1.75

Experience

1.75

 journeys

1.62

 memories

1.54

Activations Density 0.007%

mentions of personal experiences or encounters

mentions of personal experiences

No Comments

No Known Activations