INDEX

Explanations

phrases related to instructions or rules, including directives and prohibitions

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and specific structural elements of writing, particularly within lists or sections of text

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

GMT

-0.76

worm

-0.67

lock

-0.64

rosis

-0.63

 sunset

-0.63

pipe

-0.63

nings

-0.62

rop

-0.62

 starter

-0.62

raph

-0.60

POSITIVE LOGITS

who

1.06

 whom

1.05

doms

0.94

 Including

0.78

friends

0.77

groups

0.76

 Especially

0.76

 faiths

0.74

 alike

0.72

shows

0.71

Activations Density 0.710%

phrases related to instructions or rules, including directives and prohibitions

punctuation marks and specific structural elements of writing, particularly within lists or sections of text

No Comments

No Known Activations