INDEX

Explanations

words related to specific technical details and physical attributes

oai_token-act-pair · gpt-3.5-turbo

terms related to data analysis and metrics in scientific contexts

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

 Retirement

-0.81

 Accountability

-0.80

 Cash

-0.77

 Guid

-0.76

Own

-0.75

 Harmon

-0.75

Rac

-0.73

 Reserve

-0.72

 Armed

-0.72

 Charity

-0.72

POSITIVE LOGITS

ldom

1.09

geoning

0.86

oidal

0.84

ouse

0.82

anship

0.80

rylic

0.79

otine

0.78

acular

0.78

feeding

0.77

iasis

0.77

Activations Density 0.268%

words related to specific technical details and physical attributes

terms related to data analysis and metrics in scientific contexts

No Comments

No Known Activations