INDEX

Explanations

words related to outcomes or consequences

oai_token-act-pair · gpt-3.5-turbo

references to outcomes or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

horn

-0.84

 Talks

-0.79

ho

-0.75

eye

-0.69

hun

-0.67

forums

-0.62

abel

-0.62

hips

-0.60

ãĤ®

-0.59

 Ships

-0.58

POSITIVE LOGITS

 result

3.83

result

2.49

 Result

2.37

 results

2.25

 consequence

2.19

 outcome

2.08

Result

1.80

results

1.75

 resultant

1.73

 resulting

1.70

Activations Density 0.020%

words related to outcomes or consequences

references to outcomes or consequences

No Comments

No Known Activations