INDEX

Explanations

words related to the implementation or execution of plans or actions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "implemented" 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

xious

-0.79

pool

-0.78

Pacific

-0.72

bian

-0.69

 lodge

-0.66

 sands

-0.65

Sil

-0.64

fu

-0.64

away

-0.63

vol

-0.62

POSITIVE LOGITS

 implemented

1.31

 implementing

0.99

urally

0.97

 implement

0.96

 implementation

0.93

urated

0.91

 behavi

0.87

umerable

0.85

plementation

0.85

emonium

0.83

Activations Density 0.008%

words related to the implementation or execution of plans or actions

occurrences of the term "implemented" in various contexts

No Comments

No Known Activations