INDEX

Explanations

adjectives followed by a noun

oai_token-act-pair · gpt-3.5-turbo

clauses that introduce additional information or elaboration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

robe

-0.80

hoe

-0.74

acters

-0.74

verts

-0.74

amins

-0.72

ento

-0.69

 GEAR

-0.67

ESSION

-0.65

amps

-0.65

ismo

-0.65

POSITIVE LOGITS

 albeit

1.15

 unnamed

1.05

 lesser

0.96

 unidentified

0.95

 simpler

0.92

uh

0.91

 unofficial

0.90

 unpublished

0.90

 narrower

0.90

 unrelated

0.90

Activations Density 0.121%

adjectives followed by a noun

clauses that introduce additional information or elaboration

No Comments

No Known Activations