INDEX

Explanations

phrases describing imaginative scenarios

oai_token-act-pair · gpt-3.5-turbo

hypothetical scenarios and thought experiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Nonetheless

-0.77

Nevertheless

-0.75

Exit

-0.73

 Nevertheless

-0.68

"},

-0.68

particularly

-0.67

 Nonetheless

-0.66

ason

-0.65

 unfocusedRange

-0.65

so

-0.63

POSITIVE LOGITS

Imagine

1.10

 Imagine

1.09

 scenario

1.07

 hypot

0.98

 imagine

0.98

 hypothetical

0.90

 scenarios

0.89

 Suppose

0.88

 dystopian

0.81

 suddenly

0.77

Activations Density 0.396%

phrases describing imaginative scenarios

hypothetical scenarios and thought experiments

No Comments

No Known Activations