INDEX

Explanations

commands or instructions related to various processes

oai_token-act-pair · gpt-3.5-turbo

imperative or instructive phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

"—

-0.77

".[

-0.77

)].

-0.70

."[

-0.67

]."

-0.65

)—

-0.65

arth

-0.64

]).

-0.64

".

-0.63

SPONSORED

-0.62

POSITIVE LOGITS

cknowled

0.76

oret

0.70

itialized

0.60

cknow

0.58

expensive

0.56

neath

0.55

Ago

0.52

itionally

0.52

quartered

0.52

verning

0.50

Activations Density 0.599%

commands or instructions related to various processes

imperative or instructive phrases

No Comments

No Known Activations