INDEX

Explanations

words related to tracking or following something or someone

oai_token-act-pair · gpt-3.5-turbo

words related to "trace" and its variations, indicating something that can be detected or tracked

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

otos

-0.83

ows

-0.80

icum

-0.74

comes

-0.69

incial

-0.69

annis

-0.68

itch

-0.68

skill

-0.66

ottest

-0.63

ivals

-0.63

POSITIVE LOGITS

 traces

1.05

 traced

1.00

 trace

0.99

 tracing

0.96

 Trace

0.81

trace

0.80

 fossils

0.73

ability

0.72

 footprints

0.72

 bracelet

0.72

Activations Density 0.028%

words related to tracking or following something or someone

words related to "trace" and its variations, indicating something that can be detected or tracked

No Comments

No Known Activations