INDEX

Explanations

words related to statements or observations

oai_token-act-pair · gpt-3.5-turbo

references to common sayings or proverbs

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

endars

-0.93

NetMessage

-0.91

everal

-0.78

pace

-0.76

undai

-0.76

pleting

-0.75

ockets

-0.74

artifacts

-0.73

quer

-0.68

opes

-0.67

POSITIVE LOGITS

 uttered

1.07

 refrain

0.84

 echoed

0.82

 aloud

0.77

 regarding

0.77

 voiced

0.77

naire

0.75

 overlook

0.75

ariat

0.74

 ringing

0.74

Activations Density 0.243%

words related to statements or observations

references to common sayings or proverbs

No Comments

No Known Activations