INDEX

Explanations

adjectives and phrases related to acceptability or approval

oai_token-act-pair · gpt-3.5-turbo

terms related to levels of acceptability or standards in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hunter

-0.68

ences

-0.62

staking

-0.61

mares

-0.60

dragon

-0.60

eries

-0.59

stro

-0.57

etti

-0.56

 trek

-0.56

 Trip

-0.56

POSITIVE LOGITS

 acceptable

3.52

acceptable

2.49

 permissible

1.96

 unacceptable

1.96

 satisfactory

1.75

 allowable

1.75

 toler

1.70

 tolerated

1.66

 accepted

1.48

 manageable

1.45

Activations Density 0.017%

adjectives and phrases related to acceptability or approval

terms related to levels of acceptability or standards in various contexts

No Comments

No Known Activations