INDEX

Explanations

programming-related terms and code snippets

oai_token-act-pair · gpt-3.5-turbo

statements asserting the existence or condition of something

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 wills

-0.72

 elders

-0.64

worthiness

-0.63

results

-0.63

 exemptions

-0.63

 Chero

-0.62

 membranes

-0.62

 rites

-0.62

 procedures

-0.61

eers

-0.61

POSITIVE LOGITS

rael

1.36

omorphic

1.10

senal

1.10

omorph

1.09

olation

1.08

nt

1.01

ometric

1.00

olate

0.96

omer

0.93

olated

0.92

Activations Density 0.313%

programming-related terms and code snippets

statements asserting the existence or condition of something

No Comments

No Known Activations