INDEX

Explanations

phrases related to in-depth research or thorough investigation

oai_token-act-pair · gpt-3.5-turbo

the term "extensive" in a variety of contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CENT

-0.82

few

-0.71

instead

-0.71

hop

-0.70

thur

-0.69

hops

-0.67

 firmly

-0.66

ttle

-0.66

fortunately

-0.66

idas

-0.66

POSITIVE LOGITS

 amounts

0.82

 renovations

0.82

bred

0.80

 documentation

0.79

 resear

0.75

 literature

0.75

 array

0.73

 renovation

0.73

 stretches

0.73

mble

0.72

Activations Density 0.095%

phrases related to in-depth research or thorough investigation

the term "extensive" in a variety of contexts

No Comments

No Known Activations