INDEX

Explanations

phrases related to the concept of plausibility or likelihood

oai_token-act-pair · gpt-3.5-turbo

terms associated with plausible explanations and inferential reasoning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hops

-0.81

eus

-0.77

uria

-0.75

sterdam

-0.72

usterity

-0.71

une

-0.70

RAW

-0.69

antha

-0.69

ires

-0.68

scrib

-0.68

POSITIVE LOGITS

\\\\\\\\

0.85

 assurances

0.83

 enough

0.81

enough

0.79

 unbeliev

0.79

 explan

0.77

 explanations

0.76

 excuse

0.76

 explanation

0.74

 credible

0.73

Activations Density 0.036%

phrases related to the concept of plausibility or likelihood

terms associated with plausible explanations and inferential reasoning

No Comments

No Known Activations