INDEX

Explanations

words related to past tense actions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "ced" and its variations, indicating a focus on context related to actions or processes

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

 contrace

-0.78

 Scotia

-0.76

ISH

-0.67

iband

-0.66

involved

-0.66

 motto

-0.66

 Horowitz

-0.64

 magnification

-0.64

addin

-0.62

 sights

-0.62

POSITIVE LOGITS

ez

1.08

een

0.93

ragon

0.92

oing

0.87

gments

0.86

umbnail

0.85

ures

0.85

dit

0.81

ept

0.78

Activations Density 0.044%

words related to past tense actions

instances of the word "ced" and its variations, indicating a focus on context related to actions or processes

No Comments

No Known Activations