INDEX

Explanations

adjectives and verbs related to negative or critical opinions

oai_token-act-pair · gpt-3.5-turbo

adjectives and participles that express quality or condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

umbn

-0.74

othal

-0.73

ailable

-0.72

anni

-0.72

pei

-0.72

othy

-0.70

______

-0.68

athan

-0.67

obook

-0.66

ajor

-0.65

POSITIVE LOGITS

 observers

0.90

 enough

0.90

 considerations

0.87

 examples

0.85

 explanations

0.85

 assumptions

0.84

 feats

0.83

 warnings

0.83

 gestures

0.82

 quantities

0.82

Activations Density 0.381%

adjectives and verbs related to negative or critical opinions

adjectives and participles that express quality or condition

No Comments

No Known Activations