INDEX

Explanations

language related to procedural aspects or procedural terms

oai_token-act-pair · gpt-3.5-turbo

terms related to procedural aspects in various contexts

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

ofi

-0.91

renheit

-0.86

jri

-0.77

ning

-0.77

words

-0.76

wan

-0.76

amiya

-0.76

ammad

-0.75

rir

-0.75

emi

-0.74

POSITIVE LOGITS

 procedural

1.03

 safeguards

0.94

izational

0.87

 protections

0.81

 violations

0.81

 considerations

0.80

 rules

0.78

 requirements

0.76

 maneuvers

0.76

 filings

0.75

Activations Density 0.013%

language related to procedural aspects or procedural terms

terms related to procedural aspects in various contexts

No Comments

No Known Activations