INDEX

Explanations

expressions of numerical values with 'x' followed by a digit

oai_token-act-pair · gpt-3.5-turbo

mentions of the "x" variable or factor, often related to computing systems

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

éĹĺ

-0.85

Pru

-0.82

ESH

-0.74

 Fargo

-0.73

ilitarian

-0.73

EMENT

-0.73

theless

-0.73

ADRA

-0.71

kamp

-0.71

DERR

-0.69

POSITIVE LOGITS

yz

1.21

xxxxxxxx

1.12

xxxx

1.01

posed

1.00

avier

0.93

xxx

0.91

xx

0.90

iang

0.89

hair

0.79

eno

0.78

Activations Density 0.021%

expressions of numerical values with 'x' followed by a digit

mentions of the "x" variable or factor, often related to computing systems

No Comments

No Known Activations