INDEX

Explanations

mentions of "first" occurrences or events within a specific context

oai_token-act-pair · gpt-3.5-turbo

key events or notable occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 abound

-0.76

tnc

-0.64

ruciating

-0.58

 Maxim

-0.57

cdn

-0.57

 Spears

-0.57

 unfocusedRange

-0.57

ĺħ

-0.57

 Preservation

-0.57

=-=-=-=-

-0.57

POSITIVE LOGITS

 outing

0.77

 imaginable

0.75

 arrives

0.74

 hurdle

0.73

imester

0.73

 foray

0.71

hander

0.66

baugh

0.66

 hatch

0.65

nesday

0.64

Activations Density 0.415%

mentions of "first" occurrences or events within a specific context

key events or notable occurrences

No Comments

No Known Activations

mentions of "first" occurrences or events within a specific context

key events or notable occurrences

No Comments

No Known Activations