INDEX

Explanations

quotes or statements made by individuals

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "one" followed by related numerical identifiers or references

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aution

-0.65

 Enemies

-0.62

 EVENTS

-0.62

enment

-0.62

 INFO

-0.61

 sorts

-0.60

 Events

-0.59

nature

-0.59

 Companies

-0.59

ptions

-0.59

POSITIVE LOGITS

 subp

0.71

Lago

0.70

Drive

0.70

ahoo

0.69

 apiece

0.68

 staffer

0.65

hander

0.64

¿½

0.64

isen

0.64

Activations Density 0.267%

quotes or statements made by individuals

occurrences of the word "one" followed by related numerical identifiers or references

No Comments

No Known Activations