INDEX

Explanations

instances of occurrences or examples

oai_token-act-pair · gpt-3.5-turbo

references to multiple instances of occurrences or events

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

asus

-0.95

ramid

-0.72

 embr

-0.70

wig

-0.69

lasses

-0.67

 monop

-0.66

ebus

-0.66

nis

-0.65

argon

-0.64

 compass

-0.64

POSITIVE LOGITS

 involving

1.06

 cases

0.97

 occurring

0.77

 instances

0.76

0.75

 occurrence

0.72

 cited

0.71

 Cases

0.71

 ranging

0.70

 diagnosed

0.70

Activations Density 0.084%

instances of occurrences or examples

references to multiple instances of occurrences or events

No Comments

No Known Activations