INDEX

Explanations

words related to language and communication

oai_token-act-pair · gpt-3.5-turbo

statements or phrases expressing certainty and opinions about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

dule

-0.63

 packets

-0.60

 packet

-0.58

rote

-0.58

budget

-0.55

 administered

-0.55

 proposals

-0.55

 receipt

-0.54

execute

-0.54

vol

-0.53

POSITIVE LOGITS

 exacerbated

0.94

 understatement

0.91

 evidenced

0.85

 understandable

0.82

 compounded

0.81

why

0.81

 reason

0.80

 unsur

0.79

quickShipAvailable

0.79

 reflected

0.79

Activations Density 0.443%

words related to language and communication

statements or phrases expressing certainty and opinions about various subjects

No Comments

No Known Activations