INDEX

Explanations

mentions of the word "lava"

oai_token-act-pair · gpt-3.5-turbo

occurrences of names or references related to specific fictional characters, particularly in the context of creative works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

bol

-0.74

comments

-0.71

leaf

-0.68

lest

-0.66

progress

-0.66

pard

-0.66

matically

-0.65

boro

-0.65

Domin

-0.65

bread

-0.64

POSITIVE LOGITS

ptions

0.85

qua

0.85

zzi

0.83

Tir

0.74

tails

0.74

pport

0.71

lda

0.71

 Flam

0.71

IDA

0.71

fw

0.70

Activations Density 0.047%

mentions of the word "lava"

occurrences of names or references related to specific fictional characters, particularly in the context of creative works

No Comments

No Known Activations