INDEX

Explanations

phrases related to limits or boundaries

oai_token-act-pair · gpt-3.5-turbo

terms related to limitations or restrictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

rious

-0.77

alky

-0.70

ublic

-0.69

ALK

-0.68

outed

-0.65

story

-0.65

orthy

-0.64

Corn

-0.64

Rust

-0.64

PE

-0.64

POSITIVE LOGITS

 limits

1.12

 limit

0.98

 Limits

0.92

 restricts

0.90

lessness

0.82

 tolerance

0.82

 restraints

0.81

 limitations

0.79

 limiting

0.78

enges

0.77

Activations Density 0.012%

phrases related to limits or boundaries

terms related to limitations or restrictions

No Comments

No Known Activations