INDEX

Explanations

words related to causation and attribution

oai_token-act-pair · gpt-3.5-turbo

phrases indicating causation or attribution

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rooms

-0.68

 Mush

-0.64

 benches

-0.63

ahs

-0.61

erb

-0.61

iverpool

-0.61

headers

-0.59

 needle

-0.58

cgi

-0.58

ahi

-0.58

POSITIVE LOGITS

 partly

0.85

 solely

0.82

 chiefly

0.81

actionDate

0.77

 principally

0.76

 disproportionately

0.72

 attributable

0.72

SourceFile

0.70

 partially

0.69

galitarian

0.69

Activations Density 0.154%

words related to causation and attribution

phrases indicating causation or attribution

No Comments

No Known Activations