INDEX

Explanations

proper nouns related to framing or structures

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of framing 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

 Elon

-0.65

 Miche

-0.63

 Trip

-0.63

ENSE

-0.61

REDACTED

-0.60

 Mercer

-0.60

 circuit

-0.60

wana

-0.59

Charge

-0.59

Downloadha

-0.58

POSITIVE LOGITS

eworks

1.29

erate

1.20

pton

1.12

ingham

0.99

raped

0.89

ework

0.88

erity

0.85

itives

0.84

ascript

0.83

ances

0.81

Activations Density 0.041%

proper nouns related to framing or structures

terms related to the concept of framing in various contexts

No Comments

No Known Activations