INDEX

Explanations

terms related to financial allocations or funding

oai_token-act-pair · gpt-3.5-turbo

terms related to funding and budget allocations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Oracle

-0.96

âĢ¢âĢ¢âĢ¢âĢ¢

-0.76

ARDS

-0.75

icle

-0.74

jad

-0.71

KING

-0.71

ening

-0.71

liners

-0.70

uber

-0.70

ened

-0.69

POSITIVE LOGITS

itures

1.10

 appropriations

0.95

 subcommittee

0.92

ngth

0.89

ments

0.88

 appropriation

0.87

 Appropriations

0.84

mble

0.81

iture

0.80

staking

0.79

Activations Density 0.043%

terms related to financial allocations or funding

terms related to funding and budget allocations

No Comments

No Known Activations