INDEX

Explanations

words or phrases indicating a decision or a conclusion

oai_token-act-pair · gpt-3.5-turbo

repeated phrases implying a conclusion or result

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

ulton

-0.68

archives

-0.67

inen

-0.66

>>

-0.65

tein

-0.63

NYT

-0.61

ellen

-0.61

/-

-0.61

reads

-0.60

=]

-0.60

POSITIVE LOGITS

stairs

0.95

river

0.90

graded

0.89

 stairs

0.87

grading

0.86

 sidx

0.82

vote

0.76

 redes

0.74

grades

0.73

WARD

0.66

Activations Density 0.025%

words or phrases indicating a decision or a conclusion

repeated phrases implying a conclusion or result

No Comments

No Known Activations