INDEX

Explanations

references to tape or recordings, often in the context of media, devices, or actions involving tape

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.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

ancial

-0.73

Ĭ±

-0.68

ationally

-0.66

places

-0.64

å§«

-0.62

nesota

-0.60

 Democr

-0.60

ostics

-0.59

lein

-0.59

abad

-0.59

POSITIVE LOGITS

 recorder

1.08

red

1.01

 Tape

0.97

 tape

0.95

clip

0.92

 tapes

0.87

 cassette

0.84

recorded

0.81

 taped

0.81

 recordings

0.79

Activations Density 0.016%

references to tape or recordings, often in the context of media, devices, or actions involving tape

No Comments

No Known Activations