INDEX

Explanations

mentions of intentional or unintentional actions

oai_token-act-pair · gpt-3.5-turbo

terms related to intentionality in actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Tens

-0.80

ularity

-0.77

stocks

-0.77

ings

-0.73

ciating

-0.73

heit

-0.72

rooms

-0.72

eting

-0.71

INGS

-0.71

uster

-0.70

POSITIVE LOGITS

 unintentional

1.27

 intentional

1.19

 unintended

0.92

 accidental

0.82

 inadvert

0.82

idental

0.81

aneous

0.80

heon

0.77

intention

0.74

 unintentionally

0.74

Activations Density 0.014%

mentions of intentional or unintentional actions

terms related to intentionality in actions or events

No Comments

No Known Activations