INDEX

Explanations

timestamps in a specific format

oai_token-act-pair · gpt-3.5-turbo

numerical values and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 millenn

-0.76

 suprem

-0.73

 wary

-0.72

ĸļ

-0.72

istry

-0.69

 trafficking

-0.67

inery

-0.67

 traged

-0.66

 explanatory

-0.64

anooga

-0.64

POSITIVE LOGITS

.............

1.07

0.94

0.93

0.91

0.90

0.89

Activations Density 0.069%

timestamps in a specific format

numerical values and identifiers

No Comments

No Known Activations