INDEX

Explanations

numbers and names

oai_token-act-pair · gpt-3.5-turbo

phrases indicating exceptions or conditional situations

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

rypt

-0.74

 decl

-0.74

 Griff

-0.72

 Soph

-0.71

 defic

-0.70

 Ridge

-0.69

 Seraph

-0.69

sap

-0.68

Jer

-0.68

 therm

-0.66

POSITIVE LOGITS

 GOODMAN

0.96

ussian

0.85

va

0.85

UTC

0.82

anda

0.82

za

0.80

 ALSO

0.79

âĺħ

0.78

\/

0.78

ve

0.77

Activations Density 0.365%

numbers and names

phrases indicating exceptions or conditional situations

No Comments

No Known Activations