INDEX

Explanations

words related to improvement, refinement, or mastery of skills

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "hon" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

TPS

-0.83

mia

-0.74

Else

-0.72

FACE

-0.72

BOOK

-0.72

backer

-0.70

 Franch

-0.67

 Danger

-0.67

TY

-0.66

 Forth

-0.66

POSITIVE LOGITS

olulu

1.12

hon

0.96

rie

0.88

animous

0.87

ours

0.84

itives

0.83

ision

0.79

ingen

0.79

edo

0.78

ateurs

0.78

Activations Density 0.017%

words related to improvement, refinement, or mastery of skills

occurrences of the term "hon" in various contexts

No Comments

No Known Activations