INDEX

Explanations

terms related to communication laws or systems

oai_token-act-pair · gpt-3.5-turbo

references to communications legislation and related concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endon

-0.92

gling

-0.89

iless

-0.87

jury

-0.87

adium

-0.81

lein

-0.80

enes

-0.80

steen

-0.78

ilts

-0.78

uck

-0.78

POSITIVE LOGITS

 communications

1.00

communications

0.93

 channels

0.91

 networks

0.90

 communication

0.87

 protocols

0.86

 messages

0.83

 theorist

0.82

 transmissions

0.80

 systems

0.79

Activations Density 0.028%

terms related to communication laws or systems

references to communications legislation and related concepts

No Comments

No Known Activations