INDEX

Explanations

actions or events happening on the following day

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "next" indicating a sequence in time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

theless

-0.76

lees

-0.69

bos

-0.67

cca

-0.66

ans

-0.65

balls

-0.65

bows

-0.65

hist

-0.65

lee

-0.65

lua

-0.65

POSITIVE LOGITS

 step

0.99

 iteration

0.95

 generation

0.94

 installment

0.93

 logical

0.88

 chapter

0.85

 paragraph

0.84

ļéĨĴ

0.83

decade

0.83

 incarnation

0.83

Activations Density 0.034%

actions or events happening on the following day

occurrences of the word "next" indicating a sequence in time

No Comments

No Known Activations