INDEX

Explanations

phrases related to a specific American football team, the Washington Redskins

oai_token-act-pair · gpt-3.5-turbo

mentions of the Redskins football team and related context

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

judicial

-0.81

ote

-0.77

arching

-0.76

olean

-0.75

Ã¶r

-0.74

lder

-0.74

ered

-0.74

sb

-0.73

ement

-0.71

oshi

-0.70

POSITIVE LOGITS

 Redskins

0.96

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.91

 Nationals

0.90

 Capitals

0.87

istani

0.80

daq

0.79

 Express

0.78

 Chiefs

0.75

 Cousins

0.70

å£«

0.70

Activations Density 0.026%

phrases related to a specific American football team, the Washington Redskins

mentions of the Redskins football team and related context

No Comments

No Known Activations