INDEX

Explanations

mentions of discussions or talks

oai_token-act-pair · gpt-3.5-turbo

terms related to discussions and negotiations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

die

-0.66

 Manip

-0.64

flat

-0.64

rip

-0.62

older

-0.61

îĢ

-0.60

Op

-0.59

PS

-0.58

trump

-0.58

ãĥĺ

-0.57

POSITIVE LOGITS

 beforehand

0.96

 warr

0.92

 consultation

0.85

 consulted

0.81

ļéĨĴ

0.81

urion

0.80

actionDate

0.78

 internally

0.76

 feasibility

0.76

 advising

0.75

Activations Density 0.250%

mentions of discussions or talks

terms related to discussions and negotiations

No Comments

No Known Activations